Seasonal prediction of tropical cyclone activity over the north Indian Ocean using the neural network model

array:24 ["pii" => "S0187623617300115" "issn" => "01876236" "doi" => "10.20937/ATM.2015.28.04.06" "estado" => "S300" "fechaPublicacion" => "2015-10-01" "aid" => "73859" "copyright" => "Universidad Nacional Autónoma de México" "copyrightAnyo" => "2015" "documento" => "article" "crossmark" => 0 "licencia" => "http://creativecommons.org/licenses/by-nc-nd/4.0/" "subdocumento" => "fla" "cita" => "Atmósfera. 2015;28:271-81" "abierto" => array:3 [ "ES" => true "ES2" => true "LATM" => true ] "gratuito" => true "lecturas" => array:2 [ "total" => 534 "formatos" => array:3 [ "EPUB" => 22 "HTML" => 373 "PDF" => 139 ] ] "itemSiguiente" => array:19 [ "pii" => "S0187623617300127" "issn" => "01876236" "doi" => "10.20937/ATM.2015.28.04.07" "estado" => "S300" "fechaPublicacion" => "2015-10-01" "aid" => "73860" "copyright" => "Universidad Nacional Autónoma de México" "documento" => "article" "crossmark" => 0 "licencia" => "http://creativecommons.org/licenses/by-nc-nd/4.0/" "subdocumento" => "fla" "cita" => "Atmósfera. 2015;28:283-96" "abierto" => array:3 [ "ES" => true "ES2" => true "LATM" => true ] "gratuito" => true "lecturas" => array:2 [ "total" => 364 "formatos" => array:3 [ "EPUB" => 29 "HTML" => 225 "PDF" => 110 ] ] "en" => array:10 [ "idiomaDefecto" => true "titulo" => "Role of forcing in large-time behavior of vorticity equation solutions on a sphere" "tienePdf" => "en" "tieneTextoCompleto" => "en" "tieneResumen" => array:2 [ 0 => "es" 1 => "en" ] "paginas" => array:1 [ 0 => array:2 [ "paginaInicial" => "283" "paginaFinal" => "296" ] ] "contieneResumen" => array:2 [ "es" => true "en" => true ] "contieneTextoCompleto" => array:1 [ "en" => true ] "contienePdf" => array:1 [ "en" => true ] "autores" => array:1 [ 0 => array:2 [ "autoresLista" => "Yuri N. Skiba" "autores" => array:1 [ 0 => array:2 [ "nombre" => "Yuri N." "apellidos" => "Skiba" ] ] ] ] ] "idiomaDefecto" => "en" "EPUB" => "https://multimedia.elsevier.es/PublicationsMultimediaV1/item/epub/S0187623617300127?idApp=UINPBA00004N" "url" => "/01876236/0000002800000004/v1_201703180150/S0187623617300127/v1_201703180150/en/main.assets" ] "itemAnterior" => array:19 [ "pii" => "S0187623617300103" "issn" => "01876236" "doi" => "10.20937/ATM.2015.28.04.05" "estado" => "S300" "fechaPublicacion" => "2015-10-01" "aid" => "73858" "copyright" => "Universidad Nacional Autónoma de México" "documento" => "article" "crossmark" => 0 "licencia" => "http://creativecommons.org/licenses/by-nc-nd/4.0/" "subdocumento" => "fla" "cita" => "Atmósfera. 2015;28:261-9" "abierto" => array:3 [ "ES" => true "ES2" => true "LATM" => true ] "gratuito" => true "lecturas" => array:2 [ "total" => 532 "formatos" => array:3 [ "EPUB" => 28 "HTML" => 331 "PDF" => 173 ] ] "en" => array:11 [ "idiomaDefecto" => true "titulo" => "Evaluation of ensemble NWP models for dynamical downscaling of air temperature over complex topography in a hot climate: A case study from the Sultanate of Oman" "tienePdf" => "en" "tieneTextoCompleto" => "en" "tieneResumen" => array:2 [ 0 => "es" 1 => "en" ] "paginas" => array:1 [ 0 => array:2 [ "paginaInicial" => "261" "paginaFinal" => "269" ] ] "contieneResumen" => array:2 [ "es" => true "en" => true ] "contieneTextoCompleto" => array:1 [ "en" => true ] "contienePdf" => array:1 [ "en" => true ] "resumenGrafico" => array:2 [ "original" => 0 "multimedia" => array:7 [ "identificador" => "fig0025" "etiqueta" => "Fig. 5" "tipo" => "MULTIMEDIAFIGURA" "mostrarFloat" => true "mostrarDisplay" => false "figura" => array:1 [ 0 => array:4 [ "imagen" => "gr5.jpeg" "Alto" => 2395 "Ancho" => 1533 "Tamanyo" => 311849 ] ] "descripcion" => array:1 [ "en" => "Verification results for the Salalah station scatter plots for different forecasts: (a) T C-HRM-GME; (b) T C-HRM-ECMWF; (c) T C-COSMO-GME); (d) T C-COSMO-EC-MWF; (e) T C-Ensemble Mean); (f) Comparison of ensemble members, ensemble mean and observed monthly mean time series)." ] ] ] "autores" => array:2 [ 0 => array:2 [ "autoresLista" => "Yassine Charabi" "autores" => array:1 [ 0 => array:2 [ "nombre" => "Yassine" "apellidos" => "Charabi" ] ] ] 1 => array:2 [ "autoresLista" => "Sultan Al-Yahyai" "autores" => array:1 [ 0 => array:2 [ "nombre" => "Sultan" "apellidos" => "Al-Yahyai" ] ] ] ] ] "idiomaDefecto" => "en" "EPUB" => "https://multimedia.elsevier.es/PublicationsMultimediaV1/item/epub/S0187623617300103?idApp=UINPBA00004N" "url" => "/01876236/0000002800000004/v1_201703180150/S0187623617300103/v1_201703180150/en/main.assets" ] "en" => array:18 [ "idiomaDefecto" => true "titulo" => "Seasonal prediction of tropical cyclone activity over the north Indian Ocean using the neural network model" "tieneTextoCompleto" => true "paginas" => array:1 [ 0 => array:2 [ "paginaInicial" => "271" "paginaFinal" => "281" ] ] "autores" => array:2 [ 0 => array:4 [ "autoresLista" => "Sankar Nath, S.D. Kotal" "autores" => array:2 [ 0 => array:4 [ "nombre" => "Sankar" "apellidos" => "Nath" "email" => array:1 [ 0 => "sankar.nath@imd.gov.in" ] "referencia" => array:1 [ 0 => array:2 [ "etiqueta" => "*" "identificador" => "cor0005" ] ] ] 1 => array:2 [ "nombre" => "S.D." "apellidos" => "Kotal" ] ] "afiliaciones" => array:1 [ 0 => array:2 [ "entidad" => "India Meteorological Department, Mausam Bhavan, Lodi Road, New Delhi 110003, India" "identificador" => "aff0005" ] ] "correspondencia" => array:1 [ 0 => array:3 [ "identificador" => "cor0005" "etiqueta" => "*" "correspondencia" => "Corresponding author." ] ] ] 1 => array:3 [ "autoresLista" => "P.K. kundu" "autores" => array:1 [ 0 => array:2 [ "nombre" => "P.K." "apellidos" => "kundu" ] ] "afiliaciones" => array:2 [ 0 => array:2 [ "entidad" => "India Meteorological Department, Mausam Bhavan, Lodi Road, New Delhi 110003, India" "identificador" => "aff0010" ] 1 => array:2 [ "entidad" => "Department of Mathematics, Jadavpur University, Kolkata 700032, India" "identificador" => "aff0015" ] ] ] ] "resumenGrafico" => array:2 [ "original" => 0 "multimedia" => array:7 [ "identificador" => "fig0035" "etiqueta" => "Fig. 6" "tipo" => "MULTIMEDIAFIGURA" "mostrarFloat" => true "mostrarDisplay" => false "figura" => array:1 [ 0 => array:4 [ "imagen" => "gr6.jpeg" "Alto" => 561 "Ancho" => 1572 "Tamanyo" => 82483 ] ] "descripcion" => array:1 [ "en" => "Time series plots for actual and predicted TC counts from the MLR and NN methods for the testing period. The solid line with a solid circle represents the NN predicted value. The dotted line with a solid square represents the actual observation. The boldface dashed line with a solid triangle represents the MLR model predicted value." ] ] ] "textoCompleto" => "1IntroductionA natural hazard affects the environment and leads to huge economic losses and casualties. Tropical cyclones (TCs) are some of the most frequent and destructive natural hazards in TC-prone areas. In 2008, tropical cyclone Nargis was the second deadliest disaster of the decade in Myanmar. It caused 138 366 human causalities (<a class="elsevierStyleCrossRef" href="#bib0230">Vos et al., 2009</a>). So, disaster managers and planners needed high quality forecasts to save human lives and prevent property losses. Tropical cyclone activity depends on both thermodynamical and dynamical factors, which is also reported by several researchers (<a class="elsevierStyleCrossRef" href="#bib0185">Palmen, 1948</a>; <a class="elsevierStyleCrossRef" href="#bib0085">Gray, 1968</a>; <a class="elsevierStyleCrossRef" href="#bib0065">Elsberry and Jeffries, 1996</a>; <a class="elsevierStyleCrossRef" href="#bib0050">DeMaria et al., 2001</a>). The seasonal TC activity forecasts for the Australian and North Atlantic regions were first made by <a class="elsevierStyleCrossRef" href="#bib0175">Nicholls (1979)</a> and <a class="elsevierStyleCrossRef" href="#bib0095">Gray (1984 a</a>, <a class="elsevierStyleCrossRef" href="#bib0100">b</a>), respectively. Since then, several methodologies have been adopted for the seasonal TC activity forecast in different TC-prone areas of the world, such as Poisson regression models (<a class="elsevierStyleCrossRef" href="#bib0075">Elsner and Schmertmann, 1993</a>; <a class="elsevierStyleCrossRef" href="#bib0135">Lehmiller et al., 1997</a>; <a class="elsevierStyleCrossRef" href="#bib0110">Kim et al., 2010</a>), Bayesian regression models (<a class="elsevierStyleCrossRef" href="#bib0070">Elsner and Jagger, 2004</a>, <a class="elsevierStyleCrossRef" href="#bib0080">2006</a>; <a class="elsevierStyleCrossRef" href="#bib0040">Chu and Zhao, 2007</a>; <a class="elsevierStyleCrossRef" href="#bib0045">Chu et al., 2010</a>; <a class="elsevierStyleCrossRef" href="#bib0145">Lu et al., 2010</a>; <a class="elsevierStyleCrossRef" href="#bib0240">Werner and Holbrook, 2011</a>), projection pursuit regression (<a class="elsevierStyleCrossRef" href="#bib0020">Chan et al., 1998</a>, <a class="elsevierStyleCrossRef" href="#bib0025">2001</a>). However, studies of the neural network (NN) approach to seasonal cyclone activity forecasting are limited.The application of the NN model in the field of meteorology has been discussed by several researchers (<a class="elsevierStyleCrossRef" href="#bib0190">Pozzi et al., 2000</a>; <a class="elsevierStyleCrossRef" href="#bib0205">Richaume et al., 2000</a>; <a class="elsevierStyleCrossRef" href="#bib0220">Schroeder et al., 2002</a>; <a class="elsevierStyleCrossRef" href="#bib0015">Bourras et al., 2003</a>; <a class="elsevierStyleCrossRef" href="#bib0165">Mitra et al., 2010</a>). <a class="elsevierStyleCrossRef" href="#bib0160">McCann (1992)</a> and <a class="elsevierStyleCrossRef" href="#bib0130">Kuligowski and Barros (1998)</a> found that this model is superior as compared to the traditional weather prediction model. The NN model also has been applied to project future heavy rainfall events for Oahu, Hawaii (<a class="elsevierStyleCrossRef" href="#bib0180">Norton et al., 2011</a>). Other studies also show that the prediction of cyclone intensity has been improved by the artificial neural network (ANN) over the linear regression method (<a class="elsevierStyleCrossRef" href="#bib0005">Baik and Hwang, 1998</a>; <a class="elsevierStyleCrossRef" href="#bib0010">Baik and Paek, 2000</a>; <a class="elsevierStyleCrossRef" href="#bib0195">Ramírez and Veneros, 2004</a>; <a class="elsevierStyleCrossRef" href="#bib0200">Ramírez and Castro, 2006</a>).There are several studies on the genesis (<a class="elsevierStyleCrossRef" href="#bib0210">Roy Bhowmik, 2003</a>; <a class="elsevierStyleCrossRef" href="#bib0125">Kotal et al., 2009</a>; <a class="elsevierStyleCrossRef" href="#bib0170">Nath et al., 2013</a>) and intensity prediction (<a class="elsevierStyleCrossRef" href="#bib0055">Dvorak, 1975</a>; <a class="elsevierStyleCrossRef" href="#bib0215">Roy Bhowmik et al., 2007</a>; <a class="elsevierStyleCrossRef" href="#bib0120">Kotal et al., 2008</a>) of cyclones over the Indian Sea. However, in comparison the Indian Sea has received relatively limited attention, given that several studies have documented the seasonal prediction (including the NN method approach) of cyclones in other ocean basins of the world. Hence, an attempt has been made to develop an NN model to forecast seasonal TC activity over the north Indian Ocean (NIO).In the present study, the NN and multiple linear regression (MLR) using jackknife approaches have been used to predict the seasonal activity of TCs in the post-monsoon season (October, November, December) over the NIO, which has a pre-monsoon (March, April, May) and a post-monsoon (October, November, December) cyclone season. <a class="elsevierStyleCrossRef" href="#fig0005">Figure 1</a> shows the monthly distribution of TC frequency formed over the NIO from 1971 to 2013. The large inter-seasonal contrast is evident, with a highest peak occurring in November. The total frequency of TCs for the post-monsoon season from 1971 to 2013 over the NIO is presented in <a class="elsevierStyleCrossRef" href="#fig0010">Figure 2</a>.<elsevierMultimedia ident="fig0005"></elsevierMultimedia><elsevierMultimedia ident="fig0010"></elsevierMultimedia>The structure of this paper is as follows: data and methodology are described in section 2; procedures for selecting predictors are explained in section 2.1; model formulation is described in section 2.2; model evaluation is presented in section 3, and the concluding remarks are given in section 4.2Data and methodologyThe monthly tropical cyclone series of the north Indian Ocean from 1971 to 2013 was obtained from the frequency of cyclone disturbances archives of the India Meteorological Department (IMD) New Delhi (<a href="http://www.imd.gov.in/">www.imd.gov.in</a>), which is a recognized Regional Specialized Meteorological Centre (RSMC)<a name="p3"></a> for tropical cyclone warning advisories by the World Meteorological Organization (WMO). Monthly sea level pressure, zonal wind data at 700 hPa and 200 hPa, geopotential height at 500 hPa, and relative humidity at 500 hPa over the region under analysis were derived from the NCEP/NCAR reanalysis dataset for developing the model. Horizontal resolution of the dataset is 2.5° latitude×2.5° longitude.Low-pressure systems over the Indian region are classified based on the maximum sustained wind speed and the pressure deficit/number of closed isobars associated with the system. The pressure criteria are used when the system is over land and wind criteria is used when the system is over the sea. The system is classified as low if there is one closed isobar in the interval of 2 hPa; as a depression if there are two closed isobars; as a deep depression if there are three closed isobars; and as a cyclonic storm if there are four or more closed isobars. The detailed classification based on the wind criteria (<a class="elsevierStyleCrossRef" href="#bib0250">WMO, 2014</a>) is given in <a class="elsevierStyleCrossRef" href="#tbl0005">Table I</a>. Considering wind criteria, systems with wind speed of 17-27 knots are called depression and low pressure systems with maximum sustained 3-min surface winds between 28 and 33 knots are called deep depressions. Systems with maximum sustained 3-min surface winds of 34 knots or more are called cyclonic storms, which may be classified as cyclonic storms, severe cyclonic storms, very severe cyclonic storms and super cyclones.<elsevierMultimedia ident="tbl0005"></elsevierMultimedia>2.1Procedures for selecting predictorsThe modulations of seasonal TCs activity by large- scale environmental conditions have been reported by several researchers (<a class="elsevierStyleCrossRef" href="#bib0090">Gray, 1977</a>; <a class="elsevierStyleCrossRef" href="#bib0235">Watterson et al., 1995</a>; <a class="elsevierStyleCrossRef" href="#bib0040">Chu and Zhao, 2007</a>). In the present study correlation analysis between seasonal TC occurrences and the mean environmental parameters (e.g., relative humidity, wind) for the post-monsoon season over the region (50-140° e, 20° S-25° N) is used to identify physical relationships. After examining the correlation between large-scale environmental parameters and TC counts, a correlation analysis between seasonal TC occurrences for the preceding month (September) is performed to find the stability of large-scale environmental parameters. The stable parameters for September are derived as predictors. Significant correlation areas have been demarcated for each parameter. Areas with fairly large spatial extent (at least 10° latitude×and 15° longitude) have been selected in order to avoid the correlation bullseyes that sometimes exist in the NCEP/NCAR reanalysis (<a class="elsevierStyleCrossRef" href="#bib0115">Klotzbach and Philip, 2008</a>). When correlations over a particular area between 50-140° E, 20° S-25° N that are found to be statistically significant at the 95% confidence level, the parameter over the area is retained as a potential predictor variable. For a sample size of 32,<a name="p4"></a> this critical value is |0.35| when a two-tailed t-test is applied. The contour plot for the correlation between the seasonal TC frequencies over the north Indian Ocean for the month of September and all the predictors for critical domains are shown in <a class="elsevierStyleCrossRef" href="#fig0015">Figure 3a-e</a>. <a class="elsevierStyleCrossRef" href="#fig0015">Figure 3a</a> shows the correlation between the seasonal TC counts and the antecedent September month geopotential height at 500 hPa (GPH500). A strong negative correlation pattern is found in most of the Bay of Bengal and China Sea in the region under analysis. The pattern may persist and support convection and the development of TCs.<elsevierMultimedia ident="fig0015"></elsevierMultimedia><a class="elsevierStyleCrossRef" href="#fig0015">Figure 3b</a> displays the correlation between seasonal TC counts and mid tropospheric relative humidity at 500 hPa (RH500) during the antecedent month. Critical regions with significantly high positive correlations are found over the Philippine Sea and the northwest of the south China Sea. As a result of this positive correlation, higher moisture content over the aforementioned regions could be expected, leading to more TCs over the north Indian Ocean during the post-monsoon season.<a class="elsevierStyleCrossRef" href="#fig0015">Figure 3c</a> shows the correlation between seasonal TC counts and the SLP during the antecedent month. A critical area with negative correlation is found in most of the Bay of Bengal for the region under analysis. This result is physically reasonable as lower SLPs trigger higher TC frequencies.<a class="elsevierStyleCrossRef" href="#fig0020">Figure 3d</a> shows the correlation between seasonal TC counts and zonal wind at 700 hPa (U700) for the antecedent month. Critical regions with significant positive correlations are found in the Arabian Sea region.<elsevierMultimedia ident="fig0020"></elsevierMultimedia><a class="elsevierStyleCrossRef" href="#fig0020">Figure 3e</a> shows the correlation between seasonal TC counts and zonal wind at 200 hPa (U200) for the antecedent month. Critical regions with significant negative correlations are found in the Arabian Sea and the adjoining south Indian Ocean region. Accordingly, strong zonal currents at the upper level and weak at lower levels may disrupt the development of convection and cyclonic systems. It is clearly indicated that strong upper and weak lower level winds during September over the critical regions were instrumental for lower TC activity over the NOI.2.2Model formulation2.2.1Multiple linear regression modelThe MLR model is developed using the multiple linear regression technique:<elsevierMultimedia ident="eq0005"></elsevierMultimedia>where y is the dependent variable (predictant) and x1, x2,..., xn are independent variables (predictors). a1, a2,..., an are regression coefficients. The five large- scale climate variables, namely geopotential height at 500 hPa, relative humidity at 500 hPa, sea level pressure, and zonal wind at 700 hPa and 200 hPa for the antecedent month (September) are used as predictors and the seasonal number of tropical cyclones formed over the north Indian Ocean during the post monsoon season is used as predictand.The jackknife method was applied to all 32 years, with one year being removed. Thus, the model was developed for the remaining 31 years and tested on the missing year. In this way 32 predictions were obtained. Predicted values were then correlated with observations and the overall forecast skill have been determined for the training period. The skill of the testing period is evaluated using 32 years training period data as input.2.2.2Neural network modelThe neural network technique proposed here is based on the three-layer back propagation for seasonal TC frequency, using the same predictors from the multiple linear regression model and the Levenberg-Marquardt training algorithm, as shown in <a class="elsevierStyleCrossRef" href="#fig0025">Figure 4</a>. The mean square error is minimized (<a class="elsevierStyleCrossRef" href="#bib0155">Maqsood et al., 2002</a>; <a class="elsevierStyleCrossRef" href="#bib0150">Marquardt, 1963</a>) in this method. This optimization method is more powerful than the conventionally used gradient descent techniques (<a class="elsevierStyleCrossRef" href="#bib0060">El-Bakry, 2003</a>; <a class="elsevierStyleCrossRef" href="#bib0105">Hagan and Mehnaj, 1994</a>; <a class="elsevierStyleCrossRef" href="#bib0035">Cigizoglu and Kisi, 2006</a>). It has now become a standard technique for nonlinear least-square problems, widely adopted in various disciplines including atmospheric sciences for dealing with data-fitting applications (<a class="elsevierStyleCrossRef" href="#bib0165">Mitra et al., 2010</a>; <a class="elsevierStyleCrossRef" href="#bib0225">Ustaoglu et al., 2008</a>; <a class="elsevierStyleCrossRef" href="#bib0255">Young, 2006</a>; <a class="elsevierStyleCrossRef" href="#bib0030">Chase et al., 2011</a>). Considering its popularity and robustnes, the Levenberg-Marquardt algorithm (LMA) is adopted in this paper. The model contains five neurons, which correspond to the predictors used in the MLR, five neurons in the hidden layers and one neuron in the output layer, namely the seasonal number of tropical cyclones formed over the north Indian Ocean during the post monsoon seasons. The hidden layer and transfer function are determined during the network architecture design, considering that there should not be any significant overfitting<a name="p5"></a><a name="p6"></a><a name="p7"></a> and the network should have better performance. In this study, five hidden neurons are found to produce the best result.<elsevierMultimedia ident="fig0025"></elsevierMultimedia>The neuron in the output layer corresponds to the predicted TC frequency. The optimum network performance has been achieved using the tan-sigmoid transfer function from the input layer to the hidden layer and the linear transfer function from the hidden layer to the output layer. The NN model is developed using 32 year data samples. A training set and independent data samples from the remaining 11 years are used for model testing.3Model evaluationsIn this section, the skill level of both predictive models discussed above is evaluated. The performance of the model has been evaluated by the following parameters: mean value of the actual observation (O), standard deviation of the actual observation (So), mean value of the predicted variable (P), standard deviation ofthe predicted variable (Sp), and estimated values of the predicted variable Pˆi under the least-squares regression Pˆi=a+b Oi. The performance of the model is also evaluated by the “index of agreement” (d), and the systematic and unsystematic mean square errors (MSES and MSEu, respectively). As proposed by <a class="elsevierStyleCrossRef" href="#bib0245">Willmott (1982)</a>, the index of agreement and the systematic and unsystematic mean square errors are defined as:<elsevierMultimedia ident="eq0010"></elsevierMultimedia>where N is the number of observations. The better predictive models would be identified as those having lower systematic errors, unsystematic errors nearer to the RMSE, and a higher index of agreement (<a class="elsevierStyleCrossRef" href="#bib0245">Willmott, 1982</a>). In his study, <a class="elsevierStyleCrossRef" href="#bib0245">Willmott (1982)</a> also suggested that RMSEu can be interpreted as a measure of accuracy. In the present study, all the parameters described above and the mean absolute error (MAE) are computed to evaluate and compare the performance of the developed models described in the preceding section. The statistics of these parameters for the training and testing periods are presented in <a class="elsevierStyleCrossRef" href="#tbl0010">Tables II</a> and <a class="elsevierStyleCrossRef" href="#tbl0015">III</a>, respectively.<elsevierMultimedia ident="tbl0010"></elsevierMultimedia><elsevierMultimedia ident="tbl0015"></elsevierMultimedia>3.1Model performance during the training period (1971-2002)<a class="elsevierStyleCrossRef" href="#tbl0005">Table II</a> shows that statistic values P and Sp are close to the corresponding observed parameters O and So in both models, but in the MLR model P is closer to O as compared to the NN model, where Sp is closer to So. A more comprehensive evaluation has been made based in difference indices. With<a name="p8"></a> respect to MAE, there is a clear distinction between both models. The value of MAE is lower in the NN model as compared to the MLR model, which is also suggested by the RMSE. RMSE and RMSEu are higher and lower, respectively, in the NN model. This implies that the NN model is better than the MLR model, as explained by <a class="elsevierStyleCrossRef" href="#bib0245">Willmott (1982)</a>. The value of Willmott's index d also indicates that the NN model has a higher value of d than the MLR model. It can therefore be inferred that the NN model produces forecasts in better agreement with the actual TC activity formed over NIO than the MLR model, which is evident in <a class="elsevierStyleCrossRef" href="#fig0030">Figure 5</a>.<elsevierMultimedia ident="fig0030"></elsevierMultimedia><a class="elsevierStyleCrossRef" href="#fig0030">Figure 5</a> schematically presents time series plots for actual and predicted TC counts from the MLR and NN methods. It is clear from this figure that in some test cases the predicted values differ from the actual values, whereas some of them almost coincide with the actual values. Analyzing <a class="elsevierStyleCrossRef" href="#fig0030">Figure 5</a>, it can be inferred that there is somewhat a close association between the actual TC counts and those predicted by both the NN and MLR models. However, the NN predicted TC counts are closer to actual observations.3.2Model performance during the testing period (2003-2013)<a class="elsevierStyleCrossRef" href="#tbl0015">Table III</a> shows that statistics P and Sp are close to the corresponding observed parameters O and So in both models, which is also found in the training period. The value of MAE is lower in the NN model as compared to the MLR model, which is also suggested by the RMSE. RMSEs and RMSEu are higher and lower, respectively, in the NN model, which implies that the NN model is better than the MLR model as explained in the training section. Willmott's index d has a higher value in NN model than in the MLR model. It can therefore be inferred that the NN model produces forecasts in better agreement with the actual TC activity formed over NIO than the MLR model, which is evident from <a class="elsevierStyleCrossRef" href="#fig0035">Figure 6</a>. It is clear from this figure that in some test cases the predicted values differ from the actual values, whereas some of them almost coincide with the actual values. Analyzing <a class="elsevierStyleCrossRef" href="#fig0035">Figure 6</a>, it can be inferred that there is somewhat a close association between actual TC counts and those predicted by both the NN and MLR models.<elsevierMultimedia ident="fig0035"></elsevierMultimedia>The comprehensive evaluation of different indices indicates that the NN model is potentially more accurate as compared to the MLR model, which is also found in the training period. The model prediction using independent data samples is also consistent with the prediction of the development period.4Concluding remarksDue to the interannual variations of climate in the tropics and the existence of vast ocean basins, there is no guarantee that the seasonal TC prediction model developed for the Atlantic and Pacific oceans by several research teams is also applicable to the Indian Ocean. Although several studies have documented the seasonal prediction of cyclones for other ocean basins of the world, the Indian seas have received<a name="p9"></a> relatively less attention. Therefore, an attempt has been made to predict the seasonal (October, November, December) TC activity over the NIO using the NN technique. The model was developed based on monthly mean sample data of large-scale climate variables from the preceding month (September) for the period 1971-2002, and tested for the independent period 2003-2013. Using the correlation analysis between TC frequency and individual variables over the Indian Ocean and the adjacent sea area, critical regions were demarcated and their data were used to prepare predictor datasets. The five predictors considered here are geopotential height at 500 hPa, relative humidity at 500 hPa, sea level pressure, and zonal wind at 700 hPa and 200 hPa. Based on some performance parameters, the MLR model and the NN model were evaluated. Moreover, the results show that the predicted tropical cyclone count by both models is very close to the actual counts. It is noted that the skill level achieved by the NN model is better than the MLR model. The results of the development period are consistent with the independent period. In conclusion, the model appears to be promising for operational applications of TC prediction for the NIO." "textoCompletoSecciones" => array:1 [ "secciones" => array:9 [ 0 => array:3 [ "identificador" => "xres816087" "titulo" => "Resumen" "secciones" => array:1 [ 0 => array:1 [ "identificador" => "abst0005" ] ] ] 1 => array:3 [ "identificador" => "xres816088" "titulo" => "Abstract" "secciones" => array:1 [ 0 => array:1 [ "identificador" => "abst0010" ] ] ] 2 => array:2 [ "identificador" => "xpalclavsec813306" "titulo" => "Keywords" ] 3 => array:2 [ "identificador" => "sec0005" "titulo" => "Introduction" ] 4 => array:3 [ "identificador" => "sec0010" "titulo" => "Data and methodology" "secciones" => array:2 [ 0 => array:2 [ "identificador" => "sec0015" "titulo" => "Procedures for selecting predictors" ] 1 => array:3 [ "identificador" => "sec0020" "titulo" => "Model formulation" "secciones" => array:2 [ 0 => array:2 [ "identificador" => "sec0025" "titulo" => "Multiple linear regression model" ] 1 => array:2 [ "identificador" => "sec0030" "titulo" => "Neural network model" ] ] ] ] ] 5 => array:3 [ "identificador" => "sec0035" "titulo" => "Model evaluations" "secciones" => array:2 [ 0 => array:2 [ "identificador" => "sec0040" "titulo" => "Model performance during the training period (1971-2002)" ] 1 => array:2 [ "identificador" => "sec0045" "titulo" => "Model performance during the testing period (2003-2013)" ] ] ] 6 => array:2 [ "identificador" => "sec0050" "titulo" => "Concluding remarks" ] 7 => array:2 [ "identificador" => "xack273907" "titulo" => "Acknowledgments" ] 8 => array:1 [ "titulo" => "References" ] ] ] "pdfFichero" => "main.pdf" "tienePdf" => true "fechaRecibido" => "2015-02-17" "fechaAceptado" => "2015-08-05" "PalabrasClave" => array:1 [ "en" => array:1 [ 0 => array:4 [ "clase" => "keyword" "titulo" => "Keywords" "identificador" => "xpalclavsec813306" "palabras" => array:7 [ 0 => "Tropical cyclone" 1 => "seasonal prediction" 2 => "neural network" 3 => "artificial neural network" 4 => "multiple linear regression" 5 => "jackknife" 6 => "north Indian Ocean" ] ] ] ] "tieneResumen" => true "resumen" => array:2 [ "es" => array:2 [ "titulo" => "Resumen" "resumen" => "Se desarrolla un modelo de red neuronal para predecir el número estacional de ciclones tropicales (CT) que se desarrollan en el Océano índico septentrional después de la estación del monzón (octubre a diciembre). Se analizan la frecuencia de los CT y las variables climáticas de gran escala derivadas de la base de datos de reanálisis del NCEP/NCAR con resolución de 2.5×2.5° para el periodo 1971-2013. Se utilizaron datos del periodo 1971-2002 para desarrollar el modelo, y éste se probó con datos de muestreo independientes del periodo 2003-2013. Se eligieron cinco variables climáticas de gran escala (altura geopotencial a 500 hPa, humedad relativa a 500 hPa, presión superficial en el mar, y viento zonal a 700 y 200 hPa para el mes previo [septiembre]) como predictores para aplicar un análisis de correlación. Con base en algunos parámetros estadísticos de desempeño, se evalúa la eficacia del modelo de redes neuronales y los resultados se comparan con el modelo lineal de regresión múltiple. Los resultados indican que el número de ciclones tropicales calculado por medio de ambos modelos es muy similar al número real de ciclones ocurridos en cada año. Sin embargo, los resultados del modelo de redes neuronales fueron superiores a los del modelo linear de regresión múltiple, de modo que esta técnica de predicción de ciclones tropicales puede ser muy útil para propósitos operativos de predicción." ] "en" => array:2 [ "titulo" => "Abstract" "resumen" => "A neural network (NN) model is developed to predict the seasonal number of tropical cyclones (TCs) formed over the north Indian Ocean during the post-monsoon season (October, November, December). The frequency of TCs and the large scale climate variables derived from the NCEP/NCAR reanalysis dataset of resolution 2.5°×2.5° have been analyzed for the period 1971-2013. Data for the years 1971-2002 have been used for the development of the model, which is tested with independent sample data for the years 2003-2013. Applying correlation analysis, five large-scale climate variables, namely geopotential height at 500 hPa, relative humidity at 500 hPa, sea level pressure, and zonal wind at 700 hPa and 200 hPa for the antecedent month September are selected as predictors. Based on some performance parameter statistics, the performance of the NN model is evaluated and the results are compared with the multiple linear regression (MLR) model. From the results it is inferred that the predicted tropical cyclone count by both models is very close to the actual counts for both periods. However, the NN model is found to be superior to the MLR model. This tropical cyclone prediction technique may be useful for operational prediction purposes.<a name="p2"></a>" ] ] "multimedia" => array:12 [ 0 => array:7 [ "identificador" => "fig0005" "etiqueta" => "Fig. 1" "tipo" => "MULTIMEDIAFIGURA" "mostrarFloat" => true "mostrarDisplay" => false "figura" => array:1 [ 0 => array:4 [ "imagen" => "gr1.jpeg" "Alto" => 503 "Ancho" => 943 "Tamanyo" => 50230 ] ] "descripcion" => array:1 [ "en" => "Monthly distribution of all TCs formed over the north Indian Ocean during the period 1971-2013." ] ] 1 => array:7 [ "identificador" => "fig0010" "etiqueta" => "Fig. 2" "tipo" => "MULTIMEDIAFIGURA" "mostrarFloat" => true "mostrarDisplay" => false "figura" => array:1 [ 0 => array:4 [ "imagen" => "gr2.jpeg" "Alto" => 582 "Ancho" => 1142 "Tamanyo" => 78451 ] ] "descripcion" => array:1 [ "en" => "Distribution of TCs formed over the north Indian Ocean for the post-monsoon season during the period 1971-2013." ] ] 2 => array:7 [ "identificador" => "fig0015" "etiqueta" => "Fig. 3" "tipo" => "MULTIMEDIAFIGURA" "mostrarFloat" => true "mostrarDisplay" => false "figura" => array:2 [ 0 => array:1 [ "imagen" => "gr3.jpeg" ] 1 => array:1 [ "imagen" => "gr3a.jpeg" ] ] "descripcion" => array:1 [ "en" => "Correlation map between seasonal TC counts and the antecedent month (September), (a) Geopotential height at 500 hPa, (b) Relative humidity at 500 hPa, (c) Sea level pressure, The points with significant negative correlation are marked as “-” and points with positive correlation are marked as “+”." ] ] 3 => array:7 [ "identificador" => "fig0020" "etiqueta" => "Fig. 3" "tipo" => "MULTIMEDIAFIGURA" "mostrarFloat" => true "mostrarDisplay" => false "figura" => array:1 [ 0 => array:4 [ "imagen" => "gr4.jpeg" "Alto" => 734 "Ancho" => 946 "Tamanyo" => 97969 ] ] "descripcion" => array:1 [ "en" => "Correlation map between seasonal TC counts and the antecedent month (September). (d) Zonal wind at 700 hPa. (e) Zonal wind at 200 hPa. The points with significant negative correlation are marked as “–” and points with positive correlation are marked as “+”." ] ] 4 => array:7 [ "identificador" => "fig0025" "etiqueta" => "Fig. 4" "tipo" => "MULTIMEDIAFIGURA" "mostrarFloat" => true "mostrarDisplay" => false "figura" => array:1 [ 0 => array:4 [ "imagen" => "gr5.jpeg" "Alto" => 614 "Ancho" => 1474 "Tamanyo" => 114630 ] ] "descripcion" => array:1 [ "en" => "Three layer backpropagation neural network." ] ] 5 => array:7 [ "identificador" => "fig0030" "etiqueta" => "Fig. 5" "tipo" => "MULTIMEDIAFIGURA" "mostrarFloat" => true "mostrarDisplay" => false "figura" => array:1 [ 0 => array:4 [ "imagen" => "gr6.jpeg" "Alto" => 561 "Ancho" => 1572 "Tamanyo" => 82483 ] ] "descripcion" => array:1 [ "en" => "Time series plots for actual and predicted TC counts from the MLR and NN methods for the training period. The solid line with a solid circle represents the NN predicted value. The dotted line with a solid square represents the actual observation. The boldface dashed line with a solid triangle represents the predicted value from the MLR model." ] ] 6 => array:7 [ "identificador" => "fig0035" "etiqueta" => "Fig. 6" "tipo" => "MULTIMEDIAFIGURA" "mostrarFloat" => true "mostrarDisplay" => false "figura" => array:1 [ 0 => array:4 [ "imagen" => "gr6.jpeg" "Alto" => 561 "Ancho" => 1572 "Tamanyo" => 82483 ] ] "descripcion" => array:1 [ "en" => "Time series plots for actual and predicted TC counts from the MLR and NN methods for the testing period. The solid line with a solid circle represents the NN predicted value. The dotted line with a solid square represents the actual observation. The boldface dashed line with a solid triangle represents the MLR model predicted value." ] ] 7 => array:7 [ "identificador" => "tbl0005" "etiqueta" => "Table I" "tipo" => "MULTIMEDIATABLA" "mostrarFloat" => true "mostrarDisplay" => false "tabla" => array:1 [ "tablatextoimagen" => array:1 [ 0 => array:2 [ "tabla" => array:1 [ 0 => """ <table border="0" frame="\n \t\t\t\t\tvoid\n \t\t\t\t" class=""><thead title="thead"><tr title="table-row"><th class="td" title="table-head " align="left" valign="top" scope="col" style="border-bottom: 2px solid black">Type of disturbance \t\t\t\t\t\t\n \t\t\t\t</th><th class="td" title="table-head " align="center" valign="top" scope="col" style="border-bottom: 2px solid black">Corresponding wind speed (knots) \t\t\t\t\t\t\n \t\t\t\t</th></tr></thead><tbody title="tbody"><tr title="table-row"><td class="td" title="table-entry " align="left" valign="top">Low pressure area (L) \t\t\t\t\t\t\n \t\t\t\t</td><td class="td" title="table-entry " align="center" valign="top">< 17 \t\t\t\t\t\t\n \t\t\t\t</td></tr><tr title="table-row"><td class="td" title="table-entry " align="left" valign="top">Depression (D) \t\t\t\t\t\t\n \t\t\t\t</td><td class="td" title="table-entry " align="center" valign="top">17 - 27 \t\t\t\t\t\t\n \t\t\t\t</td></tr><tr title="table-row"><td class="td" title="table-entry " align="left" valign="top">Deep depression (DD) \t\t\t\t\t\t\n \t\t\t\t</td><td class="td" title="table-entry " align="center" valign="top">28 - 33 \t\t\t\t\t\t\n \t\t\t\t</td></tr><tr title="table-row"><td class="td" title="table-entry " align="left" valign="top">Cyclonic storm (CS) \t\t\t\t\t\t\n \t\t\t\t</td><td class="td" title="table-entry " align="center" valign="top">34 - 47 \t\t\t\t\t\t\n \t\t\t\t</td></tr><tr title="table-row"><td class="td" title="table-entry " align="left" valign="top">Severe cyclonic storm (SCS) \t\t\t\t\t\t\n \t\t\t\t</td><td class="td" title="table-entry " align="center" valign="top">48 - 63 \t\t\t\t\t\t\n \t\t\t\t</td></tr><tr title="table-row"><td class="td" title="table-entry " align="left" valign="top">Very severe cyclonic \t\t\t\t\t\t\n \t\t\t\t</td><td class="td" title="table-entry " align="" valign="top"> \t\t\t\t\t\t\n \t\t\t\t</td></tr><tr title="table-row"><td class="td" title="table-entry " align="left" valign="top">storm (VSCS) \t\t\t\t\t\t\n \t\t\t\t</td><td class="td" title="table-entry " align="center" valign="top">64-119 \t\t\t\t\t\t\n \t\t\t\t</td></tr><tr title="table-row"><td class="td" title="table-entry " align="left" valign="top">Super cyclone (SC) \t\t\t\t\t\t\n \t\t\t\t</td><td class="td" title="table-entry " align="center" valign="top">≥120 \t\t\t\t\t\t\n \t\t\t\t</td></tr></tbody></table> """ ] "imagenFichero" => array:1 [ 0 => "xTab1371585.png" ] ] ] ] "descripcion" => array:1 [ "en" => "Classification of low-pressure systems according to wind speed." ] ] 8 => array:7 [ "identificador" => "tbl0010" "etiqueta" => "Table II" "tipo" => "MULTIMEDIATABLA" "mostrarFloat" => true "mostrarDisplay" => false "tabla" => array:1 [ "tablatextoimagen" => array:1 [ 0 => array:2 [ "tabla" => array:1 [ 0 => """ <table border="0" frame="\n \t\t\t\t\tvoid\n \t\t\t\t" class=""><thead title="thead"><tr title="table-row"><th class="td" title="table-head " align="left" valign="top" scope="col" style="border-bottom: 2px solid black">Performance parameters \t\t\t\t\t\t\n \t\t\t\t</th><th class="td" title="table-head " align="center" valign="top" scope="col" style="border-bottom: 2px solid black">MLR \t\t\t\t\t\t\n \t\t\t\t</th><th class="td" title="table-head " align="center" valign="top" scope="col" style="border-bottom: 2px solid black">NN \t\t\t\t\t\t\n \t\t\t\t</th></tr></thead><tbody title="tbody"><tr title="table-row"><td class="td" title="table-entry " align="left" valign="top">Mean of actual observation (O) \t\t\t\t\t\t\n \t\t\t\t</td><td class="td" title="table-entry " align="char" valign="top">2.75 \t\t\t\t\t\t\n \t\t\t\t</td><td class="td" title="table-entry " align="char" valign="top">2.75 \t\t\t\t\t\t\n \t\t\t\t</td></tr><tr title="table-row"><td class="td" title="table-entry " align="left" valign="top">Mean of predicted variable (P) \t\t\t\t\t\t\n \t\t\t\t</td><td class="td" title="table-entry " align="char" valign="top">2.81 \t\t\t\t\t\t\n \t\t\t\t</td><td class="td" title="table-entry " align="char" valign="top">2.63 \t\t\t\t\t\t\n \t\t\t\t</td></tr><tr title="table-row"><td class="td" title="table-entry " align="left" valign="top">Standard deviation of actual observation (So) \t\t\t\t\t\t\n \t\t\t\t</td><td class="td" title="table-entry " align="char" valign="top">1.21 \t\t\t\t\t\t\n \t\t\t\t</td><td class="td" title="table-entry " align="char" valign="top">1.21 \t\t\t\t\t\t\n \t\t\t\t</td></tr><tr title="table-row"><td class="td" title="table-entry " align="left" valign="top">Standard deviation of predicted variables (Sp) \t\t\t\t\t\t\n \t\t\t\t</td><td class="td" title="table-entry " align="char" valign="top">0.82 \t\t\t\t\t\t\n \t\t\t\t</td><td class="td" title="table-entry " align="char" valign="top">1.02 \t\t\t\t\t\t\n \t\t\t\t</td></tr><tr title="table-row"><td class="td" title="table-entry " align="left" valign="top">Root mean square error (RMSE) \t\t\t\t\t\t\n \t\t\t\t</td><td class="td" title="table-entry " align="char" valign="top">1.0 \t\t\t\t\t\t\n \t\t\t\t</td><td class="td" title="table-entry " align="char" valign="top">0.92 \t\t\t\t\t\t\n \t\t\t\t</td></tr><tr title="table-row"><td class="td" title="table-entry " align="left" valign="top">Unsystematic root mean square error (RMSEu) \t\t\t\t\t\t\n \t\t\t\t</td><td class="td" title="table-entry " align="char" valign="top">0.88 \t\t\t\t\t\t\n \t\t\t\t</td><td class="td" title="table-entry " align="char" valign="top">0.83 \t\t\t\t\t\t\n \t\t\t\t</td></tr><tr title="table-row"><td class="td" title="table-entry " align="left" valign="top">Systematic root mean square error (RMSEs) \t\t\t\t\t\t\n \t\t\t\t</td><td class="td" title="table-entry " align="char" valign="top">0.26 \t\t\t\t\t\t\n \t\t\t\t</td><td class="td" title="table-entry " align="char" valign="top">0.28 \t\t\t\t\t\t\n \t\t\t\t</td></tr><tr title="table-row"><td class="td" title="table-entry " align="left" valign="top">Index of agreement (d) \t\t\t\t\t\t\n \t\t\t\t</td><td class="td" title="table-entry " align="char" valign="top">0.80 \t\t\t\t\t\t\n \t\t\t\t</td><td class="td" title="table-entry " align="char" valign="top">0.90 \t\t\t\t\t\t\n \t\t\t\t</td></tr><tr title="table-row"><td class="td" title="table-entry " align="left" valign="top">Mean absolute error (MAE) \t\t\t\t\t\t\n \t\t\t\t</td><td class="td" title="table-entry " align="char" valign="top">0.86 \t\t\t\t\t\t\n \t\t\t\t</td><td class="td" title="table-entry " align="char" valign="top">0.63 \t\t\t\t\t\t\n \t\t\t\t</td></tr></tbody></table> """ ] "imagenFichero" => array:1 [ 0 => "xTab1371586.png" ] ] ] ] "descripcion" => array:1 [ "en" => "Performance parameters for the training period." ] ] 9 => array:7 [ "identificador" => "tbl0015" "etiqueta" => "Table III" "tipo" => "MULTIMEDIATABLA" "mostrarFloat" => true "mostrarDisplay" => false "tabla" => array:1 [ "tablatextoimagen" => array:1 [ 0 => array:2 [ "tabla" => array:1 [ 0 => """ <table border="0" frame="\n \t\t\t\t\tvoid\n \t\t\t\t" class=""><thead title="thead"><tr title="table-row"><th class="td" title="table-head " align="left" valign="top" scope="col" style="border-bottom: 2px solid black">Performance Parameter \t\t\t\t\t\t\n \t\t\t\t</th><th class="td" title="table-head " align="center" valign="top" scope="col" style="border-bottom: 2px solid black">MLR \t\t\t\t\t\t\n \t\t\t\t</th><th class="td" title="table-head " align="center" valign="top" scope="col" style="border-bottom: 2px solid black">NN \t\t\t\t\t\t\n \t\t\t\t</th></tr></thead><tbody title="tbody"><tr title="table-row"><td class="td" title="table-entry " align="left" valign="top">Mean of actual observation (O) \t\t\t\t\t\t\n \t\t\t\t</td><td class="td" title="table-entry " align="char" valign="top">2 \t\t\t\t\t\t\n \t\t\t\t</td><td class="td" title="table-entry " align="char" valign="top">2 \t\t\t\t\t\t\n \t\t\t\t</td></tr><tr title="table-row"><td class="td" title="table-entry " align="left" valign="top">Mean of predicted variable (P) \t\t\t\t\t\t\n \t\t\t\t</td><td class="td" title="table-entry " align="char" valign="top">2.6 \t\t\t\t\t\t\n \t\t\t\t</td><td class="td" title="table-entry " align="char" valign="top">2.2 \t\t\t\t\t\t\n \t\t\t\t</td></tr><tr title="table-row"><td class="td" title="table-entry " align="left" valign="top">Standard deviation of actual observation (So) \t\t\t\t\t\t\n \t\t\t\t</td><td class="td" title="table-entry " align="char" valign="top">0.89 \t\t\t\t\t\t\n \t\t\t\t</td><td class="td" title="table-entry " align="char" valign="top">0.89 \t\t\t\t\t\t\n \t\t\t\t</td></tr><tr title="table-row"><td class="td" title="table-entry " align="left" valign="top">Standard deviation of predicted variables (Sp) \t\t\t\t\t\t\n \t\t\t\t</td><td class="td" title="table-entry " align="char" valign="top">0.60 \t\t\t\t\t\t\n \t\t\t\t</td><td class="td" title="table-entry " align="char" valign="top">0.77 \t\t\t\t\t\t\n \t\t\t\t</td></tr><tr title="table-row"><td class="td" title="table-entry " align="left" valign="top">Root mean square error (RMSE) \t\t\t\t\t\t\n \t\t\t\t</td><td class="td" title="table-entry " align="char" valign="top">0.94 \t\t\t\t\t\t\n \t\t\t\t</td><td class="td" title="table-entry " align="char" valign="top">0.51 \t\t\t\t\t\t\n \t\t\t\t</td></tr><tr title="table-row"><td class="td" title="table-entry " align="left" valign="top">Unsystematic root mean square error (RMSEu) \t\t\t\t\t\t\n \t\t\t\t</td><td class="td" title="table-entry " align="char" valign="top">0.81 \t\t\t\t\t\t\n \t\t\t\t</td><td class="td" title="table-entry " align="char" valign="top">0.40 \t\t\t\t\t\t\n \t\t\t\t</td></tr><tr title="table-row"><td class="td" title="table-entry " align="left" valign="top">Systematic root mean square error (RMSEs) \t\t\t\t\t\t\n \t\t\t\t</td><td class="td" title="table-entry " align="char" valign="top">0.19 \t\t\t\t\t\t\n \t\t\t\t</td><td class="td" title="table-entry " align="char" valign="top">0.32 \t\t\t\t\t\t\n \t\t\t\t</td></tr><tr title="table-row"><td class="td" title="table-entry " align="left" valign="top">Index of agreement (d) \t\t\t\t\t\t\n \t\t\t\t</td><td class="td" title="table-entry " align="char" valign="top">0.33 \t\t\t\t\t\t\n \t\t\t\t</td><td class="td" title="table-entry " align="char" valign="top">0.67 \t\t\t\t\t\t\n \t\t\t\t</td></tr><tr title="table-row"><td class="td" title="table-entry " align="left" valign="top">Mean absolute error (MAE) \t\t\t\t\t\t\n \t\t\t\t</td><td class="td" title="table-entry " align="char" valign="top">0.84 \t\t\t\t\t\t\n \t\t\t\t</td><td class="td" title="table-entry " align="char" valign="top">0.42 \t\t\t\t\t\t\n \t\t\t\t</td></tr></tbody></table> """ ] "imagenFichero" => array:1 [ 0 => "xTab1371587.png" ] ] ] ] "descripcion" => array:1 [ "en" => "Performance parameters for the testing period." ] ] 10 => array:6 [ "identificador" => "eq0005" "etiqueta" => "(1)" "tipo" => "MULTIMEDIAFORMULA" "mostrarFloat" => false "mostrarDisplay" => true "Formula" => array:5 [ "Matematica" => "y=a0+a1x1+a2x2+⋯+anxn," "Fichero" => "STRIPIN_si1.jpeg" "Tamanyo" => 1810 "Alto" => 13 "Ancho" => 235 ] ] 11 => array:6 [ "identificador" => "eq0010" "etiqueta" => "(2)" "tipo" => "MULTIMEDIAFORMULA" "mostrarFloat" => false "mostrarDisplay" => true "Formula" => array:5 [ "Matematica" => "d=1−∑i=1N(Pi−Oi)2/∑i=1N(Pi−O+Oi−O¯)2,    0≤d≤1MSES=1N  ∑i=1N(pˆi−Oi)2MSEu=1N  ∑i=1N(Pi−pˆ)2" "Fichero" => "STRIPIN_si4.jpeg" "Tamanyo" => 8822 "Alto" => 163 "Ancho" => 446 ] ] ] "bibliografia" => array:2 [ "titulo" => "References" "seccion" => array:1 [ 0 => array:2 [ "identificador" => "bibs0005" "bibliografiaReferencia" => array:51 [ 0 => array:3 [ "identificador" => "bib0005" "etiqueta" => "Baik and Hwang, 1998" "referencia" => array:1 [ 0 => array:2 [ "contribucion" => array:1 [ 0 => array:2 [ "titulo" => "Tropical cyclone intensity prediction using regression method and neural network." "autores" => array:1 [ 0 => array:2 [ "etal" => false "autores" => array:2 [ 0 => "J.J. Baik" 1 => "H.S. Hwang" ] ] ] ] ] "host" => array:1 [ 0 => array:1 [ "Revista" => array:5 [ "tituloSerie" => "J. Meteorol, Soc. JPN" "fecha" => "1998" "volumen" => "76" "paginaInicial" => "711" "paginaFinal" => "717" ] ] ] ] ] ] 1 => array:3 [ "identificador" => "bib0010" "etiqueta" => "Baik and Paek, 2000" "referencia" => array:1 [ 0 => array:2 [ "contribucion" => array:1 [ 0 => array:2 [ "titulo" => "A neural network model for predicting typhoon intensity" "autores" => array:1 [ 0 => array:2 [ "etal" => false "autores" => array:2 [ 0 => "J.J. Baik" 1 => "J.S. Paek" ] ] ] ] ] "host" => array:1 [ 0 => array:1 [ "Revista" => array:5 [ "tituloSerie" => "J. Meteorol. Soc. JPN" "fecha" => "2000" "volumen" => "78" "paginaInicial" => "857" "paginaFinal" => "869" ] ] ] ] ] ] 2 => array:3 [ "identificador" => "bib0015" "etiqueta" => "Bourras et al., 2003" "referencia" => array:1 [ 0 => array:2 [ "contribucion" => array:1 [ 0 => array:2 [ "titulo" => "Evaluation oflatent heat flux fields from satellites and models during SEMAPHORE" "autores" => array:1 [ 0 => array:2 [ "etal" => false "autores" => array:3 [ 0 => "D. Bourras" 1 => "W.T. Liu" 2 => "E.W. Tang" ] ] ] ] ] "host" => array:1 [ 0 => array:1 [ "Revista" => array:5 [ "tituloSerie" => "J. Appl. Meteorol." "fecha" => "2003" "volumen" => "42" "paginaInicial" => "227" "paginaFinal" => "239" ] ] ] ] ] ] 3 => array:3 [ "identificador" => "bib0020" "etiqueta" => "Chan et al., 1998" "referencia" => array:1 [ 0 => array:2 [ "contribucion" => array:1 [ 0 => array:2 [ "titulo" => "Seasonal forecasting of tropical cyclone activity over the western North Pacific and the South China Sea" "autores" => array:1 [ 0 => array:2 [ "etal" => false "autores" => array:3 [ 0 => "J.C.L. Chan" 1 => "J. Shi" 2 => "C.M. Lam" ] ] ] ] ] "host" => array:1 [ 0 => array:1 [ "Revista" => array:5 [ "tituloSerie" => "Weather Forecast." "fecha" => "1998" "volumen" => "13" "paginaInicial" => "997" "paginaFinal" => "1004" ] ] ] ] ] ] 4 => array:3 [ "identificador" => "bib0025" "etiqueta" => "Chan et al., 2001" "referencia" => array:1 [ 0 => array:2 [ "contribucion" => array:1 [ 0 => array:2 [ "titulo" => "Improvements in the seasonal forecasting of tropical cyclone activity over the western North Pacific" "autores" => array:1 [ 0 => array:2 [ "etal" => false "autores" => array:3 [ 0 => "J.C.L. Chan" 1 => "J. Shi" 2 => "K.S. Liu" ] ] ] ] ] "host" => array:1 [ 0 => array:1 [ "Revista" => array:5 [ "tituloSerie" => "Weather Forecast." "fecha" => "2001" "volumen" => "16" "paginaInicial" => "491" "paginaFinal" => "498" ] ] ] ] ] ] 5 => array:3 [ "identificador" => "bib0030" "etiqueta" => "Chase et al., 2011" "referencia" => array:1 [ 0 => array:3 [ "comentario" => "D17110, doi:10.1029/2011JD015641" "contribucion" => array:1 [ 0 => array:2 [ "titulo" => "Projecting changes in future heavy rainfall events for Oahu Hawaii: A statistical downscaling approach" "autores" => array:1 [ 0 => array:2 [ "etal" => false "autores" => array:3 [ 0 => "W.N. Chase" 1 => "C. Pao-Shin" 2 => "A.S. Thomas" ] ] ] ] ] "host" => array:1 [ 0 => array:1 [ "Revista" => array:3 [ "tituloSerie" => "J. Qeophys. Res." "fecha" => "2011" "volumen" => "116" ] ] ] ] ] ] 6 => array:3 [ "identificador" => "bib0035" "etiqueta" => "Cigizoglu and Kisi, 2006" "referencia" => array:1 [ 0 => array:2 [ "contribucion" => array:1 [ 0 => array:2 [ "titulo" => "Methods to improve the neural network performance in suspended sediment estimation" "autores" => array:1 [ 0 => array:2 [ "etal" => false "autores" => array:2 [ 0 => "H.K. Cigizoglu" 1 => "O. Kisi" ] ] ] ] ] "host" => array:1 [ 0 => array:1 [ "Revista" => array:5 [ "tituloSerie" => "J. Hydrol." "fecha" => "2006" "volumen" => "317" "paginaInicial" => "221" "paginaFinal" => "238" ] ] ] ] ] ] 7 => array:3 [ "identificador" => "bib0040" "etiqueta" => "Chu and Zhao, 2007" "referencia" => array:1 [ 0 => array:2 [ "contribucion" => array:1 [ 0 => array:2 [ "titulo" => "A Bayesian regression approach for predicting tropical cyclone activity over the central North Pacific" "autores" => array:1 [ 0 => array:2 [ "etal" => false "autores" => array:2 [ 0 => "P.S. Chu" 1 => "X. Zhao" ] ] ] ] ] "host" => array:1 [ 0 => array:1 [ "Revista" => array:5 [ "tituloSerie" => "J. Climate" "fecha" => "2007" "volumen" => "20" "paginaInicial" => "4002" "paginaFinal" => "4013" ] ] ] ] ] ] 8 => array:3 [ "identificador" => "bib0045" "etiqueta" => "Chu et al., 2010" "referencia" => array:1 [ 0 => array:3 [ "comentario" => "<a name="p10"></a>" "contribucion" => array:1 [ 0 => array:2 [ "titulo" => "Bayesian forecasting of seasonal typhoon activity: A track-pattern-oriented categorization approach" "autores" => array:1 [ 0 => array:2 [ "etal" => false "autores" => array:6 [ 0 => "P.S. Chu" 1 => "X. Zhao" 2 => "C.H. Ho" 3 => "H.S. Kim" 4 => "M.M. Lu" 5 => "J.H. Kim" ] ] ] ] ] "host" => array:1 [ 0 => array:1 [ "Revista" => array:5 [ "tituloSerie" => "J. Climate" "fecha" => "2010" "volumen" => "23" "paginaInicial" => "6654" "paginaFinal" => "6668" ] ] ] ] ] ] 9 => array:3 [ "identificador" => "bib0050" "etiqueta" => "DeMaria et al., 2001" "referencia" => array:1 [ 0 => array:2 [ "contribucion" => array:1 [ 0 => array:2 [ "titulo" => "A tropical cyclone genesis parameter for the tropical Atlantic" "autores" => array:1 [ 0 => array:2 [ "etal" => false "autores" => array:3 [ 0 => "M. DeMaria" 1 => "J.A. Knaff" 2 => "H.C. Bernadette" ] ] ] ] ] "host" => array:1 [ 0 => array:1 [ "Revista" => array:5 [ "tituloSerie" => "Weather Forecast." "fecha" => "2001" "volumen" => "16" "paginaInicial" => "219" "paginaFinal" => "233" ] ] ] ] ] ] 10 => array:3 [ "identificador" => "bib0055" "etiqueta" => "Dvorak, 1975" "referencia" => array:1 [ 0 => array:2 [ "contribucion" => array:1 [ 0 => array:2 [ "titulo" => "Tropical cyclone intensity analysis and forecasting from satellite imagery" "autores" => array:1 [ 0 => array:2 [ "etal" => false "autores" => array:1 [ 0 => "V.F. Dvorak" ] ] ] ] ] "host" => array:1 [ 0 => array:1 [ "Revista" => array:5 [ "tituloSerie" => "Mon. Weather Rev." "fecha" => "1975" "volumen" => "103" "paginaInicial" => "420" "paginaFinal" => "430" ] ] ] ] ] ] 11 => array:3 [ "identificador" => "bib0060" "etiqueta" => "E1-Bakry, 2003" "referencia" => array:1 [ 0 => array:2 [ "contribucion" => array:1 [ 0 => array:2 [ "titulo" => "Feed forward neural networks modeling for K-P interactions" "autores" => array:1 [ 0 => array:2 [ "etal" => false "autores" => array:1 [ 0 => "M.Y. E1-Bakry" ] ] ] ] ] "host" => array:1 [ 0 => array:1 [ "Revista" => array:5 [ "tituloSerie" => "Chaos Solitons Fract." "fecha" => "2003" "volumen" => "18" "paginaInicial" => "995" "paginaFinal" => "1000" ] ] ] ] ] ] 12 => array:3 [ "identificador" => "bib0065" "etiqueta" => "Elsberry and Jeffries, 1996" "referencia" => array:1 [ 0 => array:2 [ "contribucion" => array:1 [ 0 => array:2 [ "titulo" => "Vertical wind shear influences on tropical cyclone formation and intensification during TCM-92 and TCM-93" "autores" => array:1 [ 0 => array:2 [ "etal" => false "autores" => array:2 [ 0 => "R.L. Elsberry" 1 => "R. Jeffries" ] ] ] ] ] "host" => array:1 [ 0 => array:1 [ "Revista" => array:5 [ "tituloSerie" => "Mon. Weather. Rev." "fecha" => "1996" "volumen" => "124" "paginaInicial" => "1374" "paginaFinal" => "1387" ] ] ] ] ] ] 13 => array:3 [ "identificador" => "bib0070" "etiqueta" => "Elsner, 2004" "referencia" => array:1 [ 0 => array:2 [ "contribucion" => array:1 [ 0 => array:2 [ "titulo" => "A hierarchical Bayesian approach to seasonal hurricane modeling" "autores" => array:1 [ 0 => array:2 [ "etal" => false "autores" => array:2 [ 0 => "J.B. Elsner" 1 => "T.H. Jagger" ] ] ] ] ] "host" => array:1 [ 0 => array:1 [ "Revista" => array:5 [ "tituloSerie" => "J. Climate" "fecha" => "2004" "volumen" => "17" "paginaInicial" => "2813" "paginaFinal" => "2827" ] ] ] ] ] ] 14 => array:3 [ "identificador" => "bib0075" "etiqueta" => "Elsner and Schmertmann, 1993" "referencia" => array:1 [ 0 => array:2 [ "contribucion" => array:1 [ 0 => array:2 [ "titulo" => "Improving extended range seasonal predictions of intense Atlantic hurricane activity" "autores" => array:1 [ 0 => array:2 [ "etal" => false "autores" => array:2 [ 0 => "J.B. Elsner" 1 => "C.P. Schmertmann" ] ] ] ] ] "host" => array:1 [ 0 => array:1 [ "Revista" => array:5 [ "tituloSerie" => "Weather Forecast." "fecha" => "1993" "volumen" => "8" "paginaInicial" => "345" "paginaFinal" => "351" ] ] ] ] ] ] 15 => array:3 [ "identificador" => "bib0080" "etiqueta" => "Elsner and Jagger, 2006" "referencia" => array:1 [ 0 => array:2 [ "contribucion" => array:1 [ 0 => array:2 [ "titulo" => "Prediction models for annual U.S. hurricane counts" "autores" => array:1 [ 0 => array:2 [ "etal" => false "autores" => array:2 [ 0 => "J.B. Elsner" 1 => "T.H. Jagger" ] ] ] ] ] "host" => array:1 [ 0 => array:1 [ "Revista" => array:5 [ "tituloSerie" => "J. Climate" "fecha" => "2006" "volumen" => "19" "paginaInicial" => "2935" "paginaFinal" => "2952" ] ] ] ] ] ] 16 => array:3 [ "identificador" => "bib0085" "etiqueta" => "Gray, 1968" "referencia" => array:1 [ 0 => array:2 [ "contribucion" => array:1 [ 0 => array:2 [ "titulo" => "Global view of the origin of tropical disturbances and storms" "autores" => array:1 [ 0 => array:2 [ "etal" => false "autores" => array:1 [ 0 => "W.M. Gray" ] ] ] ] ] "host" => array:1 [ 0 => array:1 [ "Revista" => array:5 [ "tituloSerie" => "Mon. Weather Rev." "fecha" => "1968" "volumen" => "96" "paginaInicial" => "669" "paginaFinal" => "700" ] ] ] ] ] ] 17 => array:3 [ "identificador" => "bib0090" "etiqueta" => "Gray, 1977" "referencia" => array:1 [ 0 => array:2 [ "contribucion" => array:1 [ 0 => array:2 [ "titulo" => "Tropical cyclone genesis in the western North Pacific" "autores" => array:1 [ 0 => array:2 [ "etal" => false "autores" => array:1 [ 0 => "W.M. Gray" ] ] ] ] ] "host" => array:1 [ 0 => array:1 [ "Revista" => array:5 [ "tituloSerie" => "J. Meteorol. Soc. JPN" "fecha" => "1977" "volumen" => "55" "paginaInicial" => "465" "paginaFinal" => "482" ] ] ] ] ] ] 18 => array:3 [ "identificador" => "bib0095" "etiqueta" => "Gray, 1984a" "referencia" => array:1 [ 0 => array:3 [ "comentario" => "a" "contribucion" => array:1 [ 0 => array:2 [ "titulo" => "Atlantic seasonal hurricane frequency. Part I. El Nino and 30 hPa quasi biennial oscillation influences. Mon" "autores" => array:1 [ 0 => array:2 [ "etal" => false "autores" => array:1 [ 0 => "W.M. Gray" ] ] ] ] ] "host" => array:1 [ 0 => array:1 [ "Revista" => array:5 [ "tituloSerie" => "Weather Rev" "fecha" => "1984" "volumen" => "112" "paginaInicial" => "1649" "paginaFinal" => "1668" ] ] ] ] ] ] 19 => array:3 [ "identificador" => "bib0100" "etiqueta" => "Gray, 1984b" "referencia" => array:1 [ 0 => array:3 [ "comentario" => "b" "contribucion" => array:1 [ 0 => array:2 [ "titulo" => "Atlantic seasonal hurricane frequency. Part II. Forecasting its variability. Mon" "autores" => array:1 [ 0 => array:2 [ "etal" => false "autores" => array:1 [ 0 => "W.M. Gray" ] ] ] ] ] "host" => array:1 [ 0 => array:1 [ "Revista" => array:5 [ "tituloSerie" => "Weather Rev" "fecha" => "1984" "volumen" => "112" "paginaInicial" => "1669" "paginaFinal" => "1683" ] ] ] ] ] ] 20 => array:3 [ "identificador" => "bib0105" "etiqueta" => "Hagan and Mehnaj, 1994" "referencia" => array:1 [ 0 => array:2 [ "contribucion" => array:1 [ 0 => array:2 [ "titulo" => "Training feedforward networks with the Marquardt algorithm" "autores" => array:1 [ 0 => array:2 [ "etal" => false "autores" => array:2 [ 0 => "M.T. Hagan" 1 => "M.B. Mehnaj" ] ] ] ] ] "host" => array:1 [ 0 => array:2 [ "doi" => "10.1109/72.329697" "Revista" => array:6 [ "tituloSerie" => "IEEE Transactions on Neural Networks" "fecha" => "1994" "volumen" => "5" "paginaInicial" => "989" "paginaFinal" => "993" "link" => array:1 [ 0 => array:2 [ "url" => "https://www.ncbi.nlm.nih.gov/pubmed/18267874" "web" => "Medline" ] ] ] ] ] ] ] ] 21 => array:3 [ "identificador" => "bib0110" "etiqueta" => "Kim et al., 2010" "referencia" => array:1 [ 0 => array:2 [ "contribucion" => array:1 [ 0 => array:2 [ "titulo" => "Seasonal prediction of summertime tropical cyclone activity over the East China Sea using the least absolute deviation regression and the Poisson regression" "autores" => array:1 [ 0 => array:2 [ "etal" => false "autores" => array:4 [ 0 => "H.S. Kim" 1 => "H.H. Chang" 2 => "P.S. Chu" 3 => "J.H. Kim" ] ] ] ] ] "host" => array:1 [ 0 => array:1 [ "Revista" => array:5 [ "tituloSerie" => "Int. J. Climatol." "fecha" => "2010" "volumen" => "30" "paginaInicial" => "210" "paginaFinal" => "219" ] ] ] ] ] ] 22 => array:3 [ "identificador" => "bib0115" "etiqueta" => "Klotzbach and Philip, 2008" "referencia" => array:1 [ 0 => array:3 [ "comentario" => "doi:10.1029/2008 D 010047.1-11" "contribucion" => array:1 [ 0 => array:2 [ "titulo" => "Refinement to Atlantic basin seasonal hurricane prediction from 1 December" "autores" => array:1 [ 0 => array:2 [ "etal" => false "autores" => array:2 [ 0 => "J. Klotzbach" 1 => "J. Philip" ] ] ] ] ] "host" => array:1 [ 0 => array:1 [ "Revista" => array:4 [ "tituloSerie" => "J. Geophys. Res." "fecha" => "2008" "volumen" => "113" "paginaInicial" => "D17109" ] ] ] ] ] ] 23 => array:3 [ "identificador" => "bib0120" "etiqueta" => "Kotal et al., 2008" "referencia" => array:1 [ 0 => array:2 [ "contribucion" => array:1 [ 0 => array:2 [ "titulo" => "A statistical cyclone intensity prediction (SCIP) model for Bay of Bengal" "autores" => array:1 [ 0 => array:2 [ "etal" => false "autores" => array:4 [ 0 => "S.D. Kotal" 1 => "S.K. Roy Bhowmik" 2 => "P.K. Kundu" 3 => "A.K. Das" ] ] ] ] ] "host" => array:1 [ 0 => array:1 [ "Revista" => array:5 [ "tituloSerie" => "J. Earth Syst. Sci." "fecha" => "2008" "volumen" => "117" "paginaInicial" => "157" "paginaFinal" => "168" ] ] ] ] ] ] 24 => array:3 [ "identificador" => "bib0125" "etiqueta" => "Kotal et al., 2009" "referencia" => array:1 [ 0 => array:2 [ "contribucion" => array:1 [ 0 => array:2 [ "titulo" => "Analysis of cyclogenesis parameter for developing and nondeveloping low-pressure systems over the Indian Sea" "autores" => array:1 [ 0 => array:2 [ "etal" => false "autores" => array:3 [ 0 => "S.D. Kotal" 1 => "P.K. Kundu" 2 => "S.K. Roy Bhowmik" ] ] ] ] ] "host" => array:1 [ 0 => array:1 [ "Revista" => array:5 [ "tituloSerie" => "Nat. Hazards" "fecha" => "2009" "volumen" => "50" "paginaInicial" => "389" "paginaFinal" => "402" ] ] ] ] ] ] 25 => array:3 [ "identificador" => "bib0130" "etiqueta" => "Kuligowski and Barros, 1998" "referencia" => array:1 [ 0 => array:2 [ "contribucion" => array:1 [ 0 => array:2 [ "titulo" => "Experiments in short-term precipitation forecasting using artificial neutral networks" "autores" => array:1 [ 0 => array:2 [ "etal" => false "autores" => array:2 [ 0 => "R.J. Kuligowski" 1 => "A.P. Barros" ] ] ] ] ] "host" => array:1 [ 0 => array:1 [ "Revista" => array:5 [ "tituloSerie" => "Month Weather Rev." "fecha" => "1998" "volumen" => "126" "paginaInicial" => "470" "paginaFinal" => "482" ] ] ] ] ] ] 26 => array:3 [ "identificador" => "bib0135" "etiqueta" => "Lehmiller et al., 1997" "referencia" => array:1 [ 0 => array:2 [ "contribucion" => array:1 [ 0 => array:2 [ "titulo" => "Seasonal prediction models for North Atlantic basin hurricane location" "autores" => array:1 [ 0 => array:2 [ "etal" => false "autores" => array:3 [ 0 => "G.S. Lehmiller" 1 => "T.B. Kimberlain" 2 => "J.B. Elsner" ] ] ] ] ] "host" => array:1 [ 0 => array:1 [ "Revista" => array:5 [ "tituloSerie" => "Mon. Weather Rev." "fecha" => "1997" "volumen" => "125" "paginaInicial" => "1780" "paginaFinal" => "1791" ] ] ] ] ] ] 27 => array:3 [ "identificador" => "bib0140" "etiqueta" => "Liu and Chan, 2003" "referencia" => array:1 [ 0 => array:2 [ "contribucion" => array:1 [ 0 => array:2 [ "titulo" => "Climatological characteristics and seasonal forecasting of tropical cyclones making landfall along the South China coast" "autores" => array:1 [ 0 => array:2 [ "etal" => false "autores" => array:2 [ 0 => "K.S. Liu" 1 => "J.C.L. Chan" ] ] ] ] ] "host" => array:1 [ 0 => array:1 [ "Revista" => array:5 [ "tituloSerie" => "Mon. Weather Rev." "fecha" => "2003" "volumen" => "131" "paginaInicial" => "1650" "paginaFinal" => "1662" ] ] ] ] ] ] 28 => array:3 [ "identificador" => "bib0145" "etiqueta" => "Lu et al., 2010" "referencia" => array:1 [ 0 => array:2 [ "contribucion" => array:1 [ 0 => array:2 [ "titulo" => "Seasonal prediction of tropical cyclone activity in the vicinity of Taiwan using the Bayesian multivariate regression method" "autores" => array:1 [ 0 => array:2 [ "etal" => false "autores" => array:3 [ 0 => "M.M. Lu" 1 => "P.S. Chu" 2 => "Y.C. Lin" ] ] ] ] ] "host" => array:1 [ 0 => array:1 [ "Revista" => array:5 [ "tituloSerie" => "Weather Forecast." "fecha" => "2010" "volumen" => "25" "paginaInicial" => "1780" "paginaFinal" => "1795" ] ] ] ] ] ] 29 => array:3 [ "identificador" => "bib0150" "etiqueta" => "Marquardt, 1963" "referencia" => array:1 [ 0 => array:2 [ "contribucion" => array:1 [ 0 => array:2 [ "titulo" => "An algorithm for least-squares estimation of non-linear parameters" "autores" => array:1 [ 0 => array:2 [ "etal" => false "autores" => array:1 [ 0 => "D.W. Marquardt" ] ] ] ] ] "host" => array:1 [ 0 => array:1 [ "Revista" => array:5 [ "tituloSerie" => "J. Soc. Ind. Appl. Math." "fecha" => "1963" "volumen" => "11" "paginaInicial" => "431" "paginaFinal" => "441" ] ] ] ] ] ] 30 => array:3 [ "identificador" => "bib0155" "etiqueta" => "Maqsood et al., 2002" "referencia" => array:1 [ 0 => array:2 [ "contribucion" => array:1 [ 0 => array:2 [ "titulo" => "Intelligent weather monitoring systems using connectionist models." "autores" => array:1 [ 0 => array:2 [ "etal" => false "autores" => array:3 [ 0 => "I. Maqsood" 1 => "M.R. Khan" 2 => "A. Abraham" ] ] ] ] ] "host" => array:1 [ 0 => array:2 [ "doi" => "10.1113/JP273094" "Revista" => array:6 [ "tituloSerie" => "Neural, Parallel & Scientific Computations" "fecha" => "2002" "volumen" => "10" "paginaInicial" => "157" "paginaFinal" => "178" "link" => array:1 [ 0 => array:2 [ "url" => "https://www.ncbi.nlm.nih.gov/pubmed/28295377" "web" => "Medline" ] ] ] ] ] ] ] ] 31 => array:3 [ "identificador" => "bib0160" "etiqueta" => "McCam, 1992" "referencia" => array:1 [ 0 => array:2 [ "contribucion" => array:1 [ 0 => array:2 [ "titulo" => "A neural network short-term forecast of significant thunderstorm" "autores" => array:1 [ 0 => array:2 [ "etal" => false "autores" => array:1 [ 0 => "D.W. McCam" ] ] ] ] ] "host" => array:1 [ 0 => array:1 [ "Revista" => array:5 [ "tituloSerie" => "Weather Forecast." "fecha" => "1992" "volumen" => "7" "paginaInicial" => "525" "paginaFinal" => "534" ] ] ] ] ] ] 32 => array:3 [ "identificador" => "bib0165" "etiqueta" => "Mitra et al., 2010" "referencia" => array:1 [ 0 => array:2 [ "contribucion" => array:1 [ 0 => array:2 [ "titulo" => "A neural network approach for temperature retrieval from AMSU-A measurements onboard NOAA-15 and NOAA-16 satellites and a case study during Gonu cyclone" "autores" => array:1 [ 0 => array:2 [ "etal" => false "autores" => array:4 [ 0 => "A.K. Mitra" 1 => "P.K. Kundu" 2 => "A.K. Sharma" 3 => "S.K. Roy Bhowmik" ] ] ] ] ] "host" => array:1 [ 0 => array:1 [ "Revista" => array:5 [ "tituloSerie" => "Atmosfera" "fecha" => "2010" "volumen" => "23" "paginaInicial" => "225" "paginaFinal" => "239" ] ] ] ] ] ] 33 => array:3 [ "identificador" => "bib0170" "etiqueta" => "Nath et al., 2013" "referencia" => array:1 [ 0 => array:2 [ "contribucion" => array:1 [ 0 => array:2 [ "titulo" => "Analysis of a genesis potential parameter during pre-cyclone watch period over the Bay of Bengal" "autores" => array:1 [ 0 => array:2 [ "etal" => false "autores" => array:3 [ 0 => "S. Nath" 1 => "S.D. Kotal" 2 => "P.K. Kundu" ] ] ] ] ] "host" => array:1 [ 0 => array:1 [ "Revista" => array:5 [ "tituloSerie" => "Nat. Hazards" "fecha" => "2013" "volumen" => "65" "paginaInicial" => "2253" "paginaFinal" => "2265" ] ] ] ] ] ] 34 => array:3 [ "identificador" => "bib0175" "etiqueta" => "Nicholls, 1979" "referencia" => array:1 [ 0 => array:2 [ "contribucion" => array:1 [ 0 => array:2 [ "titulo" => "A possible method for predicting seasonal tropical cyclone activity in the Australian region" "autores" => array:1 [ 0 => array:2 [ "etal" => false "autores" => array:1 [ 0 => "N. Nicholls" ] ] ] ] ] "host" => array:1 [ 0 => array:1 [ "Revista" => array:5 [ "tituloSerie" => "Mon. Weather Rev" "fecha" => "1979" "volumen" => "107" "paginaInicial" => "1221" "paginaFinal" => "1224" ] ] ] ] ] ] 35 => array:3 [ "identificador" => "bib0180" "etiqueta" => "Norton et al., 2011" "referencia" => array:1 [ 0 => array:3 [ "comentario" => "doi:10.1029/2011JD015641" "contribucion" => array:1 [ 0 => array:2 [ "titulo" => "Estimating changes in future heavy rainfall events for Oahu Hawaii: A statistical downscaling approach" "autores" => array:1 [ 0 => array:2 [ "etal" => false "autores" => array:3 [ 0 => "C. Norton" 1 => "P.S. Chu" 2 => "T.A. Schroeder" ] ] ] ] ] "host" => array:1 [ 0 => array:1 [ "Revista" => array:4 [ "tituloSerie" => "J. Geophys. Res.-Atmos" "fecha" => "2011" "volumen" => "116" "paginaInicial" => "D17110" ] ] ] ] ] ] 36 => array:3 [ "identificador" => "bib0185" "etiqueta" => "Palmen, 1948" "referencia" => array:1 [ 0 => array:2 [ "contribucion" => array:1 [ 0 => array:2 [ "titulo" => "On the formation and structure of the tropical hurricane" "autores" => array:1 [ 0 => array:2 [ "etal" => false "autores" => array:1 [ 0 => "E.N. Palmen" ] ] ] ] ] "host" => array:1 [ 0 => array:1 [ "Revista" => array:5 [ "tituloSerie" => "Geophysica" "fecha" => "1948" "volumen" => "3" "paginaInicial" => "26" "paginaFinal" => "38" ] ] ] ] ] ] 37 => array:3 [ "identificador" => "bib0190" "etiqueta" => "Pozzi et al., 2000" "referencia" => array:1 [ 0 => array:3 [ "comentario" => "<a name="p11"></a>" "contribucion" => array:1 [ 0 => array:2 [ "titulo" => "Sea surface temperature and isotopic reconstruction from nannoplankton data using artificial neural networks" "autores" => array:1 [ 0 => array:2 [ "etal" => false "autores" => array:3 [ 0 => "M. Pozzi" 1 => "B.A. Malmgren" 2 => "S. Monechi" ] ] ] ] ] "host" => array:1 [ 0 => array:1 [ "Revista" => array:5 [ "tituloSerie" => "Palaeontol. Electron." "fecha" => "2000" "volumen" => "3" "paginaInicial" => "4" "paginaFinal" => "14" ] ] ] ] ] ] 38 => array:3 [ "identificador" => "bib0195" "etiqueta" => "Ramírez and Veneros, 2004" "referencia" => array:1 [ 0 => array:3 [ "comentario" => "May" "contribucion" => array:1 [ 0 => array:2 [ "titulo" => "Upper air information and neural networks to estimate hurricane intensity. 26th Conference on Hurricanes and Tropical Meteorology" "autores" => array:1 [ 0 => array:2 [ "etal" => false "autores" => array:2 [ 0 => "N.D. Ramírez" 1 => "A. Veneros" ] ] ] ] ] "host" => array:1 [ 0 => array:1 [ "Libro" => array:5 [ "fecha" => "2004" "paginaInicial" => "2" "paginaFinal" => "7" "editorial" => "American Meteorological Society" "editorialLocalizacion" => "Miami" ] ] ] ] ] ] 39 => array:3 [ "identificador" => "bib0200" "etiqueta" => "Ramírez and Castro, 2006" "referencia" => array:1 [ 0 => array:3 [ "comentario" => "April" "contribucion" => array:1 [ 0 => array:2 [ "titulo" => "A transfer function model to predict hurricane intensity. 27th Conference on Hurricanes and Tropical Meteorology" "autores" => array:1 [ 0 => array:2 [ "etal" => false "autores" => array:2 [ 0 => "N.D. Ramírez" 1 => "J.M. Castro" ] ] ] ] ] "host" => array:1 [ 0 => array:1 [ "Libro" => array:5 [ "fecha" => "2006" "paginaInicial" => "23" "paginaFinal" => "28" "editorial" => "American Meteorological Society" "editorialLocalizacion" => "Monterey, Ca" ] ] ] ] ] ] 40 => array:3 [ "identificador" => "bib0205" "etiqueta" => "Richaume et al., 2000" "referencia" => array:1 [ 0 => array:2 [ "contribucion" => array:1 [ 0 => array:2 [ "titulo" => "Neural network wind retrieval from ERS-1 scatterometer data" "autores" => array:1 [ 0 => array:2 [ "etal" => false "autores" => array:6 [ 0 => "P. Richaume" 1 => "F. Badran" 2 => "M. Crepon" 3 => "C. Mejia" 4 => "H. Roquet" 5 => "S. Thiria" ] ] ] ] ] "host" => array:1 [ 0 => array:1 [ "Revista" => array:5 [ "tituloSerie" => "J. Qeophys. Res." "fecha" => "2000" "volumen" => "105" "paginaInicial" => "8737" "paginaFinal" => "8751" ] ] ] ] ] ] 41 => array:3 [ "identificador" => "bib0210" "etiqueta" => "Roy Bhowmik, 2003" "referencia" => array:1 [ 0 => array:2 [ "contribucion" => array:1 [ 0 => array:2 [ "titulo" => "An evaluation of cyclone genesis parameter over the Bay of Bengal using modal analysis" "autores" => array:1 [ 0 => array:2 [ "etal" => false "autores" => array:1 [ 0 => "S.K. Roy Bhowmik" ] ] ] ] ] "host" => array:1 [ 0 => array:1 [ "Revista" => array:5 [ "tituloSerie" => "Mausam" "fecha" => "2003" "volumen" => "54" "paginaInicial" => "351" "paginaFinal" => "358" ] ] ] ] ] ] 42 => array:3 [ "identificador" => "bib0215" "etiqueta" => "Roy Bhowmik et al., 2007" "referencia" => array:1 [ 0 => array:2 [ "contribucion" => array:1 [ 0 => array:2 [ "titulo" => "An empirical model for predicting intensity of tropical cyclone over the Bay of Bengal" "autores" => array:1 [ 0 => array:2 [ "etal" => false "autores" => array:3 [ 0 => "S.K. Roy Bhowmik" 1 => "S.D. Kotal" 2 => "S.R. Kalsi" ] ] ] ] ] "host" => array:1 [ 0 => array:1 [ "Revista" => array:5 [ "tituloSerie" => "Nat. Hazards" "fecha" => "2007" "volumen" => "41" "paginaInicial" => "447" "paginaFinal" => "455" ] ] ] ] ] ] 43 => array:3 [ "identificador" => "bib0220" "etiqueta" => "Schroeder et al., 2002" "referencia" => array:1 [ 0 => array:2 [ "contribucion" => array:1 [ 0 => array:2 [ "titulo" => "Artificial-neural network- based atmospheric correction algorithm: Application to MERIS data" "autores" => array:1 [ 0 => array:2 [ "etal" => false "autores" => array:4 [ 0 => "T. Schroeder" 1 => "J. Fischer" 2 => "M. Schaale" 3 => "F. Fell" ] ] ] ] ] "host" => array:1 [ 0 => array:1 [ "Revista" => array:5 [ "tituloSerie" => "Proc. SPIE. Int. Soc. Opt. Eng." "fecha" => "2002" "volumen" => "4892" "paginaInicial" => "124" "paginaFinal" => "132" ] ] ] ] ] ] 44 => array:3 [ "identificador" => "bib0225" "etiqueta" => "Ustaoglu et al., 2008" "referencia" => array:1 [ 0 => array:2 [ "contribucion" => array:1 [ 0 => array:2 [ "titulo" => "Forecast of daily mean, maximum and minimum temperature time series by three artificial neural network methods" "autores" => array:1 [ 0 => array:2 [ "etal" => false "autores" => array:3 [ 0 => "B. Ustaoglu" 1 => "H.K. Cigizoglu" 2 => "M. Karaca" ] ] ] ] ] "host" => array:1 [ 0 => array:1 [ "Revista" => array:5 [ "tituloSerie" => "Meteorol. Appl." "fecha" => "2008" "volumen" => "15" "paginaInicial" => "431" "paginaFinal" => "445" ] ] ] ] ] ] 45 => array:3 [ "identificador" => "bib0230" "etiqueta" => "Vos et al., 2009" "referencia" => array:1 [ 0 => array:1 [ "referenciaCompleta" => "Vos F., J. Rodriguez, R. Below and D. Guha-Sapir, 2009. Annual disaster statistical review 2008. Centre for Research on the Epidemiology of Disasters (CRED), Brussels, Belgium, 33 pp. Available at: <a href="http://www.cred.be/sites/default/files/ADSR_2009.pdf">http://www.cred.be/sites/default/files/ADSR_2009.pdf</a>." ] ] ] 46 => array:3 [ "identificador" => "bib0235" "etiqueta" => "Watterson et al., 1995" "referencia" => array:1 [ 0 => array:2 [ "contribucion" => array:1 [ 0 => array:2 [ "titulo" => "Seasonal and interannual variability of tropical cyclogenesis: diagnostics from large-scale fields" "autores" => array:1 [ 0 => array:2 [ "etal" => false "autores" => array:3 [ 0 => "I.G. Watterson" 1 => "J.L. Evans" 2 => "B.F. Ryan" ] ] ] ] ] "host" => array:1 [ 0 => array:1 [ "Revista" => array:5 [ "tituloSerie" => "J. Climate" "fecha" => "1995" "volumen" => "8" "paginaInicial" => "3052" "paginaFinal" => "3066" ] ] ] ] ] ] 47 => array:3 [ "identificador" => "bib0240" "etiqueta" => "Werner and Holbrook, 2011" "referencia" => array:1 [ 0 => array:2 [ "contribucion" => array:1 [ 0 => array:2 [ "titulo" => "A Bayesian forecast model of Australian region tropical cyclone formation" "autores" => array:1 [ 0 => array:2 [ "etal" => false "autores" => array:2 [ 0 => "A. Werner" 1 => "N.J. Holbrook" ] ] ] ] ] "host" => array:1 [ 0 => array:1 [ "Revista" => array:5 [ "tituloSerie" => "J Climate" "fecha" => "2011" "volumen" => "24" "paginaInicial" => "6114" "paginaFinal" => "6131" ] ] ] ] ] ] 48 => array:3 [ "identificador" => "bib0245" "etiqueta" => "Willmott, 1982" "referencia" => array:1 [ 0 => array:2 [ "contribucion" => array:1 [ 0 => array:2 [ "titulo" => "Some comments on the evaluation of model performance" "autores" => array:1 [ 0 => array:2 [ "etal" => false "autores" => array:1 [ 0 => "C.J. Willmott" ] ] ] ] ] "host" => array:1 [ 0 => array:1 [ "Revista" => array:5 [ "tituloSerie" => "B. Am. Meteorol. Soc." "fecha" => "1982" "volumen" => "63" "paginaInicial" => "1309" "paginaFinal" => "1313" ] ] ] ] ] ] 49 => array:3 [ "identificador" => "bib0250" "etiqueta" => "WMO, 2014" "referencia" => array:1 [ 0 => array:1 [ "referenciaCompleta" => "WMO, 2014. Tropical cyclone operational plan for the Bay of Bengal and the Arabian Sea. Technical document WMO/TD No. 84. (Tropical Cyclone Programme Report No. TCP-21.) World Meteorological Organization, Geneva. Available at: <a href="http://www.wmo.int/pages//prog/www/tcp/documents/TCP-21Edition2014_final.pdf">www.wmo.int/pages//prog/www/tcp/documents/TCP-21Edition2014_final.pdf</a>." ] ] ] 50 => array:3 [ "identificador" => "bib0255" "etiqueta" => "Young, 2006" "referencia" => array:1 [ 0 => array:3 [ "comentario" => "doi:10.1029/2006JC003540" "contribucion" => array:1 [ 0 => array:2 [ "titulo" => "Directional spectra of hurricane wind waves" "autores" => array:1 [ 0 => array:2 [ "etal" => false "autores" => array:1 [ 0 => "I.R. Young" ] ] ] ] ] "host" => array:1 [ 0 => array:1 [ "Revista" => array:4 [ "tituloSerie" => "J. Qeophys. Res." "fecha" => "2006" "volumen" => "111" "paginaInicial" => "C08020" ] ] ] ] ] ] ] ] ] ] "agradecimientos" => array:1 [ 0 => array:4 [ "identificador" => "xack273907" "titulo" => "Acknowledgments" "texto" => "The authors are grateful to the Director General of Meteorology, India Meteorological Department, New Delhi for providing all the facilities to carry out this research work. The authors acknowledge the use of NCEP data in this research work. Authors are also grateful with the anonymous reviewers for their suggestions for improving the paper." "vista" => "all" ] ] ] "idiomaDefecto" => "en" "url" => "/01876236/0000002800000004/v1_201703180150/S0187623617300115/v1_201703180150/en/main.assets" "Apartado" => null "PDF" => "https://static.elsevier.es/multimedia/01876236/0000002800000004/v1_201703180150/S0187623617300115/v1_201703180150/en/main.pdf?idApp=UINPBA00004N&text.app=https://www.elsevier.es/" "EPUB" => "https://multimedia.elsevier.es/PublicationsMultimediaV1/item/epub/S0187623617300115?idApp=UINPBA00004N"]

Statistics

Sankar Nath

Corresponding author

sankar.nath@imd.gov.in

Corresponding author.

, S.D. Kotal

India Meteorological Department, Mausam Bhavan, Lodi Road, New Delhi 110003, India

P.K. kundu

India Meteorological Department, Mausam Bhavan, Lodi Road, New Delhi 110003, India

Department of Mathematics, Jadavpur University, Kolkata 700032, India

Read

3264

Times
was read the article

592

Total PDF

2672

Total HTML

Share statistics

 array:24 [
  "pii" => "S0187623617300115"
  "issn" => "01876236"
  "doi" => "10.20937/ATM.2015.28.04.06"
  "estado" => "S300"
  "fechaPublicacion" => "2015-10-01"
  "aid" => "73859"
  "copyright" => "Universidad Nacional Aut&#243;noma de M&#233;xico"
  "copyrightAnyo" => "2015"
  "documento" => "article"
  "crossmark" => 0
  "licencia" => "http://creativecommons.org/licenses/by-nc-nd/4.0/"
  "subdocumento" => "fla"
  "cita" => "Atm&#243;sfera. 2015;28:271-81"
  "abierto" => array:3 [
    "ES" => true
    "ES2" => true
    "LATM" => true
  ]
  "gratuito" => true
  "lecturas" => array:2 [
    "total" => 534
    "formatos" => array:3 [
      "EPUB" => 22
      "HTML" => 373
      "PDF" => 139
    ]
  ]
  "itemSiguiente" => array:19 [
    "pii" => "S0187623617300127"
    "issn" => "01876236"
    "doi" => "10.20937/ATM.2015.28.04.07"
    "estado" => "S300"
    "fechaPublicacion" => "2015-10-01"
    "aid" => "73860"
    "copyright" => "Universidad Nacional Aut&#243;noma de M&#233;xico"
    "documento" => "article"
    "crossmark" => 0
    "licencia" => "http://creativecommons.org/licenses/by-nc-nd/4.0/"
    "subdocumento" => "fla"
    "cita" => "Atm&#243;sfera. 2015;28:283-96"
    "abierto" => array:3 [
      "ES" => true
      "ES2" => true
      "LATM" => true
    ]
    "gratuito" => true
    "lecturas" => array:2 [
      "total" => 364
      "formatos" => array:3 [
        "EPUB" => 29
        "HTML" => 225
        "PDF" => 110
      ]
    ]
    "en" => array:10 [
      "idiomaDefecto" => true
      "titulo" => "Role of forcing in large-time behavior of vorticity equation solutions on a sphere"
      "tienePdf" => "en"
      "tieneTextoCompleto" => "en"
      "tieneResumen" => array:2 [
        0 => "es"
        1 => "en"
      ]
      "paginas" => array:1 [
        0 => array:2 [
          "paginaInicial" => "283"
          "paginaFinal" => "296"
        ]
      ]
      "contieneResumen" => array:2 [
        "es" => true
        "en" => true
      ]
      "contieneTextoCompleto" => array:1 [
        "en" => true
      ]
      "contienePdf" => array:1 [
        "en" => true
      ]
      "autores" => array:1 [
        0 => array:2 [
          "autoresLista" => "Yuri N&#46; Skiba"
          "autores" => array:1 [
            0 => array:2 [
              "nombre" => "Yuri N&#46;"
              "apellidos" => "Skiba"
            ]
          ]
        ]
      ]
    ]
    "idiomaDefecto" => "en"
    "EPUB" => "https://multimedia.elsevier.es/PublicationsMultimediaV1/item/epub/S0187623617300127?idApp=UINPBA00004N"
    "url" => "/01876236/0000002800000004/v1_201703180150/S0187623617300127/v1_201703180150/en/main.assets"
  ]
  "itemAnterior" => array:19 [
    "pii" => "S0187623617300103"
    "issn" => "01876236"
    "doi" => "10.20937/ATM.2015.28.04.05"
    "estado" => "S300"
    "fechaPublicacion" => "2015-10-01"
    "aid" => "73858"
    "copyright" => "Universidad Nacional Aut&#243;noma de M&#233;xico"
    "documento" => "article"
    "crossmark" => 0
    "licencia" => "http://creativecommons.org/licenses/by-nc-nd/4.0/"
    "subdocumento" => "fla"
    "cita" => "Atm&#243;sfera. 2015;28:261-9"
    "abierto" => array:3 [
      "ES" => true
      "ES2" => true
      "LATM" => true
    ]
    "gratuito" => true
    "lecturas" => array:2 [
      "total" => 532
      "formatos" => array:3 [
        "EPUB" => 28
        "HTML" => 331
        "PDF" => 173
      ]
    ]
    "en" => array:11 [
      "idiomaDefecto" => true
      "titulo" => "Evaluation of ensemble NWP models for dynamical downscaling of air temperature over complex topography in a hot climate&#58; A case study from the Sultanate of Oman"
      "tienePdf" => "en"
      "tieneTextoCompleto" => "en"
      "tieneResumen" => array:2 [
        0 => "es"
        1 => "en"
      ]
      "paginas" => array:1 [
        0 => array:2 [
          "paginaInicial" => "261"
          "paginaFinal" => "269"
        ]
      ]
      "contieneResumen" => array:2 [
        "es" => true
        "en" => true
      ]
      "contieneTextoCompleto" => array:1 [
        "en" => true
      ]
      "contienePdf" => array:1 [
        "en" => true
      ]
      "resumenGrafico" => array:2 [
        "original" => 0
        "multimedia" => array:7 [
          "identificador" => "fig0025"
          "etiqueta" => "Fig&#46; 5"
          "tipo" => "MULTIMEDIAFIGURA"
          "mostrarFloat" => true
          "mostrarDisplay" => false
          "figura" => array:1 [
            0 => array:4 [
              "imagen" => "gr5.jpeg"
              "Alto" => 2395
              "Ancho" => 1533
              "Tamanyo" => 311849
            ]
          ]
          "descripcion" => array:1 [
            "en" => "<p id="spar0035" class="elsevierStyleSimplePara elsevierViewall">Verification results for the Salalah station scatter plots for different forecasts&#58; &#40;a&#41; T C-HRM-GME&#59; &#40;b&#41; T C-HRM-ECMWF&#59; &#40;c&#41; T C-COSMO-GME&#41;&#59; &#40;d&#41; T C-COSMO-EC-MWF&#59; &#40;e&#41; T C-Ensemble Mean&#41;&#59; &#40;f&#41; Comparison of ensemble members&#44; ensemble mean and observed monthly mean time series&#41;&#46;</p>"
          ]
        ]
      ]
      "autores" => array:2 [
        0 => array:2 [
          "autoresLista" => "Yassine Charabi"
          "autores" => array:1 [
            0 => array:2 [
              "nombre" => "Yassine"
              "apellidos" => "Charabi"
            ]
          ]
        ]
        1 => array:2 [
          "autoresLista" => "Sultan Al-Yahyai"
          "autores" => array:1 [
            0 => array:2 [
              "nombre" => "Sultan"
              "apellidos" => "Al-Yahyai"
            ]
          ]
        ]
      ]
    ]
    "idiomaDefecto" => "en"
    "EPUB" => "https://multimedia.elsevier.es/PublicationsMultimediaV1/item/epub/S0187623617300103?idApp=UINPBA00004N"
    "url" => "/01876236/0000002800000004/v1_201703180150/S0187623617300103/v1_201703180150/en/main.assets"
  ]
  "en" => array:18 [
    "idiomaDefecto" => true
    "titulo" => "Seasonal prediction of tropical cyclone activity over the north Indian Ocean using the neural network model"
    "tieneTextoCompleto" => true
    "paginas" => array:1 [
      0 => array:2 [
        "paginaInicial" => "271"
        "paginaFinal" => "281"
      ]
    ]
    "autores" => array:2 [
      0 => array:4 [
        "autoresLista" => "Sankar Nath, S&#46;D&#46; Kotal"
        "autores" => array:2 [
          0 => array:4 [
            "nombre" => "Sankar"
            "apellidos" => "Nath"
            "email" => array:1 [
              0 => "sankar&#46;nath&#64;imd&#46;gov&#46;in"
            ]
            "referencia" => array:1 [
              0 => array:2 [
                "etiqueta" => "<span class="elsevierStyleSup">&#42;</span>"
                "identificador" => "cor0005"
              ]
            ]
          ]
          1 => array:2 [
            "nombre" => "S&#46;D&#46;"
            "apellidos" => "Kotal"
          ]
        ]
        "afiliaciones" => array:1 [
          0 => array:2 [
            "entidad" => "India Meteorological Department&#44; Mausam Bhavan&#44; Lodi Road&#44; New Delhi 110003&#44; India"
            "identificador" => "aff0005"
          ]
        ]
        "correspondencia" => array:1 [
          0 => array:3 [
            "identificador" => "cor0005"
            "etiqueta" => "&#42;"
            "correspondencia" => "Corresponding author&#46;"
          ]
        ]
      ]
      1 => array:3 [
        "autoresLista" => "P&#46;K&#46; kundu"
        "autores" => array:1 [
          0 => array:2 [
            "nombre" => "P&#46;K&#46;"
            "apellidos" => "kundu"
          ]
        ]
        "afiliaciones" => array:2 [
          0 => array:2 [
            "entidad" => "India Meteorological Department&#44; Mausam Bhavan&#44; Lodi Road&#44; New Delhi 110003&#44; India"
            "identificador" => "aff0010"
          ]
          1 => array:2 [
            "entidad" => "Department of Mathematics&#44; Jadavpur University&#44; Kolkata 700032&#44; India"
            "identificador" => "aff0015"
          ]
        ]
      ]
    ]
    "resumenGrafico" => array:2 [
      "original" => 0
      "multimedia" => array:7 [
        "identificador" => "fig0035"
        "etiqueta" => "Fig&#46; 6"
        "tipo" => "MULTIMEDIAFIGURA"
        "mostrarFloat" => true
        "mostrarDisplay" => false
        "figura" => array:1 [
          0 => array:4 [
            "imagen" => "gr6.jpeg"
            "Alto" => 561
            "Ancho" => 1572
            "Tamanyo" => 82483
          ]
        ]
        "descripcion" => array:1 [
          "en" => "<p id="spar0045" class="elsevierStyleSimplePara elsevierViewall">Time series plots for actual and predicted TC counts from the MLR and NN methods for the testing period&#46; The solid line with a solid circle represents the NN predicted value&#46; The dotted line with a solid square represents the actual observation&#46; The boldface dashed line with a solid triangle represents the MLR model predicted value&#46;</p>"
        ]
      ]
    ]
    "textoCompleto" => "<span class="elsevierStyleSections"><span id="sec0005" class="elsevierStyleSection elsevierViewall"><span class="elsevierStyleLabel">1</span><span class="elsevierStyleSectionTitle" id="sect0020">Introduction</span><p id="par0005" class="elsevierStylePara elsevierViewall">A natural hazard affects the environment and leads to huge economic losses and casualties&#46; Tropical cyclones &#40;TCs&#41; are some of the most frequent and destructive natural hazards in TC-prone areas&#46; In 2008&#44; tropical cyclone Nargis was the second deadliest disaster of the decade in Myanmar&#46; It caused 138 366 human causalities &#40;<a class="elsevierStyleCrossRef" href="#bib0230">Vos <span class="elsevierStyleItalic">et al&#46;&#44;</span> 2009</a>&#41;&#46; So&#44; disaster managers and planners needed high quality forecasts to save human lives and prevent property losses&#46; Tropical cyclone activity depends on both thermodynamical and dynamical factors&#44; which is also reported by several researchers &#40;<a class="elsevierStyleCrossRef" href="#bib0185">Palmen&#44; 1948</a>&#59; <a class="elsevierStyleCrossRef" href="#bib0085">Gray&#44; 1968</a>&#59; <a class="elsevierStyleCrossRef" href="#bib0065">Elsberry and Jeffries&#44; 1996</a>&#59; <a class="elsevierStyleCrossRef" href="#bib0050">DeMaria <span class="elsevierStyleItalic">et al&#46;&#44;</span> 2001</a>&#41;&#46; The seasonal TC activity forecasts for the Australian and North Atlantic regions were first made by <a class="elsevierStyleCrossRef" href="#bib0175">Nicholls &#40;1979&#41;</a> and <a class="elsevierStyleCrossRef" href="#bib0095">Gray &#40;1984 a</a>&#44; <a class="elsevierStyleCrossRef" href="#bib0100">b</a>&#41;&#44; respectively&#46; Since then&#44; several methodologies have been adopted for the seasonal TC activity forecast in different TC-prone areas of the world&#44; such as Poisson regression models &#40;<a class="elsevierStyleCrossRef" href="#bib0075">Elsner and Schmertmann&#44; 1993</a>&#59; <a class="elsevierStyleCrossRef" href="#bib0135">Lehmiller <span class="elsevierStyleItalic">et al&#46;&#44;</span> 1997</a>&#59; <a class="elsevierStyleCrossRef" href="#bib0110">Kim <span class="elsevierStyleItalic">et al&#46;&#44;</span> 2010</a>&#41;&#44; Bayesian regression models &#40;<a class="elsevierStyleCrossRef" href="#bib0070">Elsner and Jagger&#44; 2004</a>&#44; <a class="elsevierStyleCrossRef" href="#bib0080">2006</a>&#59; <a class="elsevierStyleCrossRef" href="#bib0040">Chu and Zhao&#44; 2007</a>&#59; <a class="elsevierStyleCrossRef" href="#bib0045">Chu <span class="elsevierStyleItalic">et al&#46;&#44;</span> 2010</a>&#59; <a class="elsevierStyleCrossRef" href="#bib0145">Lu <span class="elsevierStyleItalic">et al&#46;&#44;</span> 2010</a>&#59; <a class="elsevierStyleCrossRef" href="#bib0240">Werner and Holbrook&#44; 2011</a>&#41;&#44; projection pursuit regression &#40;<a class="elsevierStyleCrossRef" href="#bib0020">Chan <span class="elsevierStyleItalic">et al&#46;&#44;</span> 1998</a>&#44; <a class="elsevierStyleCrossRef" href="#bib0025">2001</a>&#41;&#46; However&#44; studies of the neural network &#40;NN&#41; approach to seasonal cyclone activity forecasting are limited&#46;</p><p id="par0010" class="elsevierStylePara elsevierViewall">The application of the NN model in the field of meteorology has been discussed by several researchers &#40;<a class="elsevierStyleCrossRef" href="#bib0190">Pozzi <span class="elsevierStyleItalic">et al&#46;&#44;</span> 2000</a>&#59; <a class="elsevierStyleCrossRef" href="#bib0205">Richaume <span class="elsevierStyleItalic">et al&#46;&#44;</span> 2000</a>&#59; <a class="elsevierStyleCrossRef" href="#bib0220">Schroeder <span class="elsevierStyleItalic">et al&#46;&#44;</span> 2002</a>&#59; <a class="elsevierStyleCrossRef" href="#bib0015">Bourras <span class="elsevierStyleItalic">et al&#46;&#44;</span> 2003</a>&#59; <a class="elsevierStyleCrossRef" href="#bib0165">Mitra <span class="elsevierStyleItalic">et al&#46;&#44;</span> 2010</a>&#41;&#46; <a class="elsevierStyleCrossRef" href="#bib0160">McCann &#40;1992&#41;</a> and <a class="elsevierStyleCrossRef" href="#bib0130">Kuligowski and Barros &#40;1998&#41;</a> found that this model is superior as compared to the traditional weather prediction model&#46; The NN model also has been applied to project future heavy rainfall events for Oahu&#44; Hawaii &#40;<a class="elsevierStyleCrossRef" href="#bib0180">Norton <span class="elsevierStyleItalic">et al</span>&#46;&#44; 2011</a>&#41;&#46; Other studies also show that the prediction of cyclone intensity has been improved by the artificial neural network &#40;ANN&#41; over the linear regression method &#40;<a class="elsevierStyleCrossRef" href="#bib0005">Baik and Hwang&#44; 1998</a>&#59; <a class="elsevierStyleCrossRef" href="#bib0010">Baik and Paek&#44; 2000</a>&#59; <a class="elsevierStyleCrossRef" href="#bib0195">Ram&#237;rez and Veneros&#44; 2004</a>&#59; <a class="elsevierStyleCrossRef" href="#bib0200">Ram&#237;rez and Castro&#44; 2006</a>&#41;&#46;</p><p id="par0015" class="elsevierStylePara elsevierViewall">There are several studies on the genesis &#40;<a class="elsevierStyleCrossRef" href="#bib0210">Roy Bhowmik&#44; 2003</a>&#59; <a class="elsevierStyleCrossRef" href="#bib0125">Kotal <span class="elsevierStyleItalic">et al&#46;&#44;</span> 2009</a>&#59; <a class="elsevierStyleCrossRef" href="#bib0170">Nath <span class="elsevierStyleItalic">et al&#46;&#44;</span> 2013</a>&#41; and intensity prediction &#40;<a class="elsevierStyleCrossRef" href="#bib0055">Dvorak&#44; 1975</a>&#59; <a class="elsevierStyleCrossRef" href="#bib0215">Roy Bhowmik <span class="elsevierStyleItalic">et al&#46;&#44;</span> 2007</a>&#59; <a class="elsevierStyleCrossRef" href="#bib0120">Kotal <span class="elsevierStyleItalic">et al&#46;&#44;</span> 2008</a>&#41; of cyclones over the Indian Sea&#46; However&#44; in comparison the Indian Sea has received relatively limited attention&#44; given that several studies have documented the seasonal prediction &#40;including the NN method approach&#41; of cyclones in other ocean basins of the world&#46; Hence&#44; an attempt has been made to develop an NN model to forecast seasonal TC activity over the north Indian Ocean &#40;NIO&#41;&#46;</p><p id="par0020" class="elsevierStylePara elsevierViewall">In the present study&#44; the NN and multiple linear regression &#40;MLR&#41; using jackknife approaches have been used to predict the seasonal activity of TCs in the post-monsoon season &#40;October&#44; November&#44; December&#41; over the NIO&#44; which has a pre-monsoon &#40;March&#44; April&#44; May&#41; and a post-monsoon &#40;October&#44; November&#44; December&#41; cyclone season&#46; <a class="elsevierStyleCrossRef" href="#fig0005">Figure 1</a> shows the monthly distribution of TC frequency formed over the NIO from 1971 to 2013&#46; The large inter-seasonal contrast is evident&#44; with a highest peak occurring in November&#46; The total frequency of TCs for the post-monsoon season from 1971 to 2013 over the NIO is presented in <a class="elsevierStyleCrossRef" href="#fig0010">Figure 2</a>&#46;</p><elsevierMultimedia ident="fig0005"></elsevierMultimedia><elsevierMultimedia ident="fig0010"></elsevierMultimedia><p id="par0025" class="elsevierStylePara elsevierViewall">The structure of this paper is as follows&#58; data and methodology are described in section 2&#59; procedures for selecting predictors are explained in section 2&#46;1&#59; model formulation is described in section 2&#46;2&#59; model evaluation is presented in section 3&#44; and the concluding remarks are given in section 4&#46;</p></span><span id="sec0010" class="elsevierStyleSection elsevierViewall"><span class="elsevierStyleLabel">2</span><span class="elsevierStyleSectionTitle" id="sect0025">Data and methodology</span><p id="par0030" class="elsevierStylePara elsevierViewall">The monthly tropical cyclone series of the north Indian Ocean from 1971 to 2013 was obtained from the frequency of cyclone disturbances archives of the India Meteorological Department &#40;IMD&#41; New Delhi &#40;<a href="http://www.imd.gov.in/">www&#46;imd&#46;gov&#46;in</a>&#41;&#44; which is a recognized Regional Specialized Meteorological Centre &#40;RSMC&#41;<a name="p3"></a> for tropical cyclone warning advisories by the World Meteorological Organization &#40;WMO&#41;&#46; Monthly sea level pressure&#44; zonal wind data at 700 hPa and 200 hPa&#44; geopotential height at 500 hPa&#44; and relative humidity at 500 hPa over the region under analysis were derived from the NCEP&#47;NCAR reanalysis dataset for developing the model&#46; Horizontal resolution of the dataset is 2&#46;5&#176; latitude<span class="elsevierStyleHsp" style=""></span>&#215;<span class="elsevierStyleHsp" style=""></span>2&#46;5&#176; longitude&#46;</p><p id="par0035" class="elsevierStylePara elsevierViewall">Low-pressure systems over the Indian region are classified based on the maximum sustained wind speed and the pressure deficit&#47;number of closed isobars associated with the system&#46; The pressure criteria are used when the system is over land and wind criteria is used when the system is over the sea&#46; The system is classified as low if there is one closed isobar in the interval of 2 hPa&#59; as a depression if there are two closed isobars&#59; as a deep depression if there are three closed isobars&#59; and as a cyclonic storm if there are four or more closed isobars&#46; The detailed classification based on the wind criteria &#40;<a class="elsevierStyleCrossRef" href="#bib0250">WMO&#44; 2014</a>&#41; is given in <a class="elsevierStyleCrossRef" href="#tbl0005">Table I</a>&#46; Considering wind criteria&#44; systems with wind speed of 17-27 knots are called depression and low pressure systems with maximum sustained 3-min surface winds between 28 and 33 knots are called deep depressions&#46; Systems with maximum sustained 3-min surface winds of 34 knots or more are called cyclonic storms&#44; which may be classified as cyclonic storms&#44; severe cyclonic storms&#44; very severe cyclonic storms and super cyclones&#46;</p><elsevierMultimedia ident="tbl0005"></elsevierMultimedia><span id="sec0015" class="elsevierStyleSection elsevierViewall"><span class="elsevierStyleLabel">2&#46;1</span><span class="elsevierStyleSectionTitle" id="sect0030">Procedures for selecting predictors</span><p id="par0040" class="elsevierStylePara elsevierViewall">The modulations of seasonal TCs activity by large- scale environmental conditions have been reported by several researchers &#40;<a class="elsevierStyleCrossRef" href="#bib0090">Gray&#44; 1977</a>&#59; <a class="elsevierStyleCrossRef" href="#bib0235">Watterson <span class="elsevierStyleItalic">et al&#46;&#44;</span> 1995</a>&#59; <a class="elsevierStyleCrossRef" href="#bib0040">Chu and Zhao&#44; 2007</a>&#41;&#46; In the present study correlation analysis between seasonal TC occurrences and the mean environmental parameters &#40;e&#46;g&#46;&#44; relative humidity&#44; wind&#41; for the post-monsoon season over the region &#40;50-140&#176; e&#44; 20&#176; S-25&#176; N&#41; is used to identify physical relationships&#46; After examining the correlation between large-scale environmental parameters and TC counts&#44; a correlation analysis between seasonal TC occurrences for the preceding month &#40;September&#41; is performed to find the stability of large-scale environmental parameters&#46; The stable parameters for September are derived as predictors&#46; Significant correlation areas have been demarcated for each parameter&#46; Areas with fairly large spatial extent &#40;at least 10&#176; latitude<span class="elsevierStyleHsp" style=""></span>&#215;<span class="elsevierStyleHsp" style=""></span>and 15&#176; longitude&#41; have been selected in order to avoid the correlation bullseyes that sometimes exist in the NCEP&#47;NCAR reanalysis &#40;<a class="elsevierStyleCrossRef" href="#bib0115">Klotzbach and Philip&#44; 2008</a>&#41;&#46; When correlations over a particular area between 50-140&#176; E&#44; 20&#176; S-25&#176; N that are found to be statistically significant at the 95&#37; confidence level&#44; the parameter over the area is retained as a potential predictor variable&#46; For a sample size of 32&#44;<a name="p4"></a> this critical value is &#124;0&#46;35&#124; when a two-tailed <span class="elsevierStyleItalic">t</span>-test is applied&#46; The contour plot for the correlation between the seasonal TC frequencies over the north Indian Ocean for the month of September and all the predictors for critical domains are shown in <a class="elsevierStyleCrossRef" href="#fig0015">Figure 3a-e</a>&#46; <a class="elsevierStyleCrossRef" href="#fig0015">Figure 3a</a> shows the correlation between the seasonal TC counts and the antecedent September month geopotential height at 500 hPa &#40;GPH500&#41;&#46; A strong negative correlation pattern is found in most of the Bay of Bengal and China Sea in the region under analysis&#46; The pattern may persist and support convection and the development of TCs&#46;</p><elsevierMultimedia ident="fig0015"></elsevierMultimedia><p id="par0045" class="elsevierStylePara elsevierViewall"><a class="elsevierStyleCrossRef" href="#fig0015">Figure 3b</a> displays the correlation between seasonal TC counts and mid tropospheric relative humidity at 500 hPa &#40;RH500&#41; during the antecedent month&#46; Critical regions with significantly high positive correlations are found over the Philippine Sea and the northwest of the south China Sea&#46; As a result of this positive correlation&#44; higher moisture content over the aforementioned regions could be expected&#44; leading to more TCs over the north Indian Ocean during the post-monsoon season&#46;</p><p id="par0050" class="elsevierStylePara elsevierViewall"><a class="elsevierStyleCrossRef" href="#fig0015">Figure 3c</a> shows the correlation between seasonal TC counts and the SLP during the antecedent month&#46; A critical area with negative correlation is found in most of the Bay of Bengal for the region under analysis&#46; This result is physically reasonable as lower SLPs trigger higher TC frequencies&#46;</p><p id="par0055" class="elsevierStylePara elsevierViewall"><a class="elsevierStyleCrossRef" href="#fig0020">Figure 3d</a> shows the correlation between seasonal TC counts and zonal wind at 700 hPa &#40;U700&#41; for the antecedent month&#46; Critical regions with significant positive correlations are found in the Arabian Sea region&#46;</p><elsevierMultimedia ident="fig0020"></elsevierMultimedia><p id="par0060" class="elsevierStylePara elsevierViewall"><a class="elsevierStyleCrossRef" href="#fig0020">Figure 3e</a> shows the correlation between seasonal TC counts and zonal wind at 200 hPa &#40;U200&#41; for the antecedent month&#46; Critical regions with significant negative correlations are found in the Arabian Sea and the adjoining south Indian Ocean region&#46; Accordingly&#44; strong zonal currents at the upper level and weak at lower levels may disrupt the development of convection and cyclonic systems&#46; It is clearly indicated that strong upper and weak lower level winds during September over the critical regions were instrumental for lower TC activity over the NOI&#46;</p></span><span id="sec0020" class="elsevierStyleSection elsevierViewall"><span class="elsevierStyleLabel">2&#46;2</span><span class="elsevierStyleSectionTitle" id="sect0035">Model formulation</span><span id="sec0025" class="elsevierStyleSection elsevierViewall"><span class="elsevierStyleLabel">2&#46;2&#46;1</span><span class="elsevierStyleSectionTitle" id="sect0040">Multiple linear regression model</span><p id="par0065" class="elsevierStylePara elsevierViewall">The MLR model is developed using the multiple linear regression technique&#58;<elsevierMultimedia ident="eq0005"></elsevierMultimedia></p><p id="par0070" class="elsevierStylePara elsevierViewall">where <span class="elsevierStyleItalic">y</span> is the dependent variable &#40;predictant&#41; and <span class="elsevierStyleItalic">x</span><span class="elsevierStyleInf"><span class="elsevierStyleItalic">1</span></span><span class="elsevierStyleItalic">&#44; x</span><span class="elsevierStyleInf"><span class="elsevierStyleItalic">2</span></span><span class="elsevierStyleItalic">&#44;&#46;&#46;&#46;&#44; x</span><span class="elsevierStyleInf"><span class="elsevierStyleItalic">n</span></span> are independent variables &#40;predictors&#41;&#46; a<span class="elsevierStyleInf">1</span>&#44; a<span class="elsevierStyleInf">2</span>&#44;&#46;&#46;&#46;&#44; a<span class="elsevierStyleInf">n</span> are regression coefficients&#46; The five large- scale climate variables&#44; namely geopotential height at 500 hPa&#44; relative humidity at 500 hPa&#44; sea level pressure&#44; and zonal wind at 700 hPa and 200 hPa for the antecedent month &#40;September&#41; are used as predictors and the seasonal number of tropical cyclones formed over the north Indian Ocean during the post monsoon season is used as predictand&#46;</p><p id="par0075" class="elsevierStylePara elsevierViewall">The jackknife method was applied to all 32 years&#44; with one year being removed&#46; Thus&#44; the model was developed for the remaining 31 years and tested on the missing year&#46; In this way 32 predictions were obtained&#46; Predicted values were then correlated with observations and the overall forecast skill have been determined for the training period&#46; The skill of the testing period is evaluated using 32 years training period data as input&#46;</p></span><span id="sec0030" class="elsevierStyleSection elsevierViewall"><span class="elsevierStyleLabel">2&#46;2&#46;2</span><span class="elsevierStyleSectionTitle" id="sect0045">Neural network model</span><p id="par0080" class="elsevierStylePara elsevierViewall">The neural network technique proposed here is based on the three-layer back propagation for seasonal TC frequency&#44; using the same predictors from the multiple linear regression model and the Levenberg-Marquardt training algorithm&#44; as shown in <a class="elsevierStyleCrossRef" href="#fig0025">Figure 4</a>&#46; The mean square error is minimized &#40;<a class="elsevierStyleCrossRef" href="#bib0155">Maqsood <span class="elsevierStyleItalic">et al&#46;&#44;</span> 2002</a>&#59; <a class="elsevierStyleCrossRef" href="#bib0150">Marquardt&#44; 1963</a>&#41; in this method&#46; This optimization method is more powerful than the conventionally used gradient descent techniques &#40;<a class="elsevierStyleCrossRef" href="#bib0060">El-Bakry&#44; 2003</a>&#59; <a class="elsevierStyleCrossRef" href="#bib0105">Hagan and Mehnaj&#44; 1994</a>&#59; <a class="elsevierStyleCrossRef" href="#bib0035">Cigizoglu and Kisi&#44; 2006</a>&#41;&#46; It has now become a standard technique for nonlinear least-square problems&#44; widely adopted in various disciplines including atmospheric sciences for dealing with data-fitting applications &#40;<a class="elsevierStyleCrossRef" href="#bib0165">Mitra <span class="elsevierStyleItalic">et al&#46;&#44;</span> 2010</a>&#59; <a class="elsevierStyleCrossRef" href="#bib0225">Ustaoglu <span class="elsevierStyleItalic">et al&#46;&#44;</span> 2008</a>&#59; <a class="elsevierStyleCrossRef" href="#bib0255">Young&#44; 2006</a>&#59; <a class="elsevierStyleCrossRef" href="#bib0030">Chase <span class="elsevierStyleItalic">et al&#46;&#44;</span> 2011</a>&#41;&#46; Considering its popularity and robustnes&#44; the Levenberg-Marquardt algorithm &#40;LMA&#41; is adopted in this paper&#46; The model contains five neurons&#44; which correspond to the predictors used in the MLR&#44; five neurons in the hidden layers and one neuron in the output layer&#44; namely the seasonal number of tropical cyclones formed over the north Indian Ocean during the post monsoon seasons&#46; The hidden layer and transfer function are determined during the network architecture design&#44; considering that there should not be any significant overfitting<a name="p5"></a><a name="p6"></a><a name="p7"></a> and the network should have better performance&#46; In this study&#44; five hidden neurons are found to produce the best result&#46;</p><elsevierMultimedia ident="fig0025"></elsevierMultimedia><p id="par0085" class="elsevierStylePara elsevierViewall">The neuron in the output layer corresponds to the predicted TC frequency&#46; The optimum network performance has been achieved using the tan-sigmoid transfer function from the input layer to the hidden layer and the linear transfer function from the hidden layer to the output layer&#46; The NN model is developed using 32 year data samples&#46; A training set and independent data samples from the remaining 11 years are used for model testing&#46;</p></span></span></span><span id="sec0035" class="elsevierStyleSection elsevierViewall"><span class="elsevierStyleLabel">3</span><span class="elsevierStyleSectionTitle" id="sect0050">Model evaluations</span><p id="par0090" class="elsevierStylePara elsevierViewall">In this section&#44; the skill level of both predictive models discussed above is evaluated&#46; The performance of the model has been evaluated by the following parameters&#58; mean value of the actual observation &#40;O&#41;&#44; standard deviation of the actual observation &#40;<span class="elsevierStyleItalic">S</span><span class="elsevierStyleInf"><span class="elsevierStyleItalic">o</span></span>&#41;&#44; mean value of the predicted variable &#40;P&#41;&#44; standard deviation ofthe predicted variable &#40;<span class="elsevierStyleItalic">S</span><span class="elsevierStyleInf"><span class="elsevierStyleItalic">p</span></span>&#41;&#44; and estimated values of the predicted variable P&#710;i under the least-squares regression P&#710;i&#61;a&#43;b&#8201;Oi<span class="elsevierStyleItalic">&#46;</span> The performance of the model is also evaluated by the &#8220;index of agreement&#8221; &#40;<span class="elsevierStyleItalic">d</span>&#41;&#44; and the systematic and unsystematic mean square errors &#40;MSE<span class="elsevierStyleInf">S</span> and MSE<span class="elsevierStyleInf">u</span>&#44; respectively&#41;&#46; As proposed by <a class="elsevierStyleCrossRef" href="#bib0245">Willmott &#40;1982&#41;</a>&#44; the index of agreement and the systematic and unsystematic mean square errors are defined as&#58;<elsevierMultimedia ident="eq0010"></elsevierMultimedia></p><p id="par0095" class="elsevierStylePara elsevierViewall">where N is the number of observations&#46; The better predictive models would be identified as those having lower systematic errors&#44; unsystematic errors nearer to the RMSE&#44; and a higher index of agreement &#40;<a class="elsevierStyleCrossRef" href="#bib0245">Willmott&#44; 1982</a>&#41;&#46; In his study&#44; <a class="elsevierStyleCrossRef" href="#bib0245">Willmott &#40;1982&#41;</a> also suggested that RMSEu can be interpreted as a measure of accuracy&#46; In the present study&#44; all the parameters described above and the mean absolute error &#40;MAE&#41; are computed to evaluate and compare the performance of the developed models described in the preceding section&#46; The statistics of these parameters for the training and testing periods are presented in <a class="elsevierStyleCrossRef" href="#tbl0010">Tables II</a> and <a class="elsevierStyleCrossRef" href="#tbl0015">III</a>&#44; respectively&#46;</p><elsevierMultimedia ident="tbl0010"></elsevierMultimedia><elsevierMultimedia ident="tbl0015"></elsevierMultimedia><span id="sec0040" class="elsevierStyleSection elsevierViewall"><span class="elsevierStyleLabel">3&#46;1</span><span class="elsevierStyleSectionTitle" id="sect0055">Model performance during the training period &#40;1971-2002&#41;</span><p id="par0100" class="elsevierStylePara elsevierViewall"><a class="elsevierStyleCrossRef" href="#tbl0005">Table II</a> shows that statistic values P and <span class="elsevierStyleItalic">S</span><span class="elsevierStyleInf"><span class="elsevierStyleItalic">p</span></span> are close to the corresponding observed parameters <span class="elsevierStyleItalic">O</span> and <span class="elsevierStyleItalic">S</span><span class="elsevierStyleInf"><span class="elsevierStyleItalic">o</span></span> in both models&#44; but in the MLR model <span class="elsevierStyleItalic">P</span> is closer to <span class="elsevierStyleItalic">O</span> as compared to the NN model&#44; where <span class="elsevierStyleItalic">S</span><span class="elsevierStyleInf"><span class="elsevierStyleItalic">p</span></span> is closer to <span class="elsevierStyleItalic">S</span><span class="elsevierStyleInf"><span class="elsevierStyleItalic">o</span></span>&#46; A more comprehensive evaluation has been made based in difference indices&#46; With<a name="p8"></a> respect to MAE&#44; there is a clear distinction between both models&#46; The value of MAE is lower in the NN model as compared to the MLR model&#44; which is also suggested by the RMSE&#46; RMSE and RMSEu are higher and lower&#44; respectively&#44; in the NN model&#46; This implies that the NN model is better than the MLR model&#44; as explained by <a class="elsevierStyleCrossRef" href="#bib0245">Willmott &#40;1982&#41;</a>&#46; The value of Willmott&#39;s index <span class="elsevierStyleItalic">d</span> also indicates that the NN model has a higher value of <span class="elsevierStyleItalic">d</span> than the MLR model&#46; It can therefore be inferred that the NN model produces forecasts in better agreement with the actual TC activity formed over NIO than the MLR model&#44; which is evident in <a class="elsevierStyleCrossRef" href="#fig0030">Figure 5</a>&#46;</p><elsevierMultimedia ident="fig0030"></elsevierMultimedia><p id="par0105" class="elsevierStylePara elsevierViewall"><a class="elsevierStyleCrossRef" href="#fig0030">Figure 5</a> schematically presents time series plots for actual and predicted TC counts from the MLR and NN methods&#46; It is clear from this figure that in some test cases the predicted values differ from the actual values&#44; whereas some of them almost coincide with the actual values&#46; Analyzing <a class="elsevierStyleCrossRef" href="#fig0030">Figure 5</a>&#44; it can be inferred that there is somewhat a close association between the actual TC counts and those predicted by both the NN and MLR models&#46; However&#44; the NN predicted TC counts are closer to actual observations&#46;</p></span><span id="sec0045" class="elsevierStyleSection elsevierViewall"><span class="elsevierStyleLabel">3&#46;2</span><span class="elsevierStyleSectionTitle" id="sect0060">Model performance during the testing period &#40;2003-2013&#41;</span><p id="par0110" class="elsevierStylePara elsevierViewall"><a class="elsevierStyleCrossRef" href="#tbl0015">Table III</a> shows that statistics P and <span class="elsevierStyleItalic">S</span><span class="elsevierStyleInf"><span class="elsevierStyleItalic">p</span></span> are close to the corresponding observed parameters <span class="elsevierStyleItalic">O</span> and <span class="elsevierStyleItalic">S</span><span class="elsevierStyleInf"><span class="elsevierStyleItalic">o</span></span> in both models&#44; which is also found in the training period&#46; The value of MAE is lower in the NN model as compared to the MLR model&#44; which is also suggested by the RMSE&#46; RMSE<span class="elsevierStyleInf">s</span> and RMSE<span class="elsevierStyleInf">u</span> are higher and lower&#44; respectively&#44; in the NN model&#44; which implies that the NN model is better than the MLR model as explained in the training section&#46; Willmott&#39;s index <span class="elsevierStyleItalic">d</span> has a higher value in NN model than in the MLR model&#46; It can therefore be inferred that the NN model produces forecasts in better agreement with the actual TC activity formed over NIO than the MLR model&#44; which is evident from <a class="elsevierStyleCrossRef" href="#fig0035">Figure 6</a>&#46; It is clear from this figure that in some test cases the predicted values differ from the actual values&#44; whereas some of them almost coincide with the actual values&#46; Analyzing <a class="elsevierStyleCrossRef" href="#fig0035">Figure 6</a>&#44; it can be inferred that there is somewhat a close association between actual TC counts and those predicted by both the NN and MLR models&#46;</p><elsevierMultimedia ident="fig0035"></elsevierMultimedia><p id="par0115" class="elsevierStylePara elsevierViewall">The comprehensive evaluation of different indices indicates that the NN model is potentially more accurate as compared to the MLR model&#44; which is also found in the training period&#46; The model prediction using independent data samples is also consistent with the prediction of the development period&#46;</p></span></span><span id="sec0050" class="elsevierStyleSection elsevierViewall"><span class="elsevierStyleLabel">4</span><span class="elsevierStyleSectionTitle" id="sect0065">Concluding remarks</span><p id="par0120" class="elsevierStylePara elsevierViewall">Due to the interannual variations of climate in the tropics and the existence of vast ocean basins&#44; there is no guarantee that the seasonal TC prediction model developed for the Atlantic and Pacific oceans by several research teams is also applicable to the Indian Ocean&#46; Although several studies have documented the seasonal prediction of cyclones for other ocean basins of the world&#44; the Indian seas have received<a name="p9"></a> relatively less attention&#46; Therefore&#44; an attempt has been made to predict the seasonal &#40;October&#44; November&#44; December&#41; TC activity over the NIO using the NN technique&#46; The model was developed based on monthly mean sample data of large-scale climate variables from the preceding month &#40;September&#41; for the period 1971-2002&#44; and tested for the independent period 2003-2013&#46; Using the correlation analysis between TC frequency and individual variables over the Indian Ocean and the adjacent sea area&#44; critical regions were demarcated and their data were used to prepare predictor datasets&#46; The five predictors considered here are geopotential height at 500 hPa&#44; relative humidity at 500 hPa&#44; sea level pressure&#44; and zonal wind at 700 hPa and 200 hPa&#46; Based on some performance parameters&#44; the MLR model and the NN model were evaluated&#46; Moreover&#44; the results show that the predicted tropical cyclone count by both models is very close to the actual counts&#46; It is noted that the skill level achieved by the NN model is better than the MLR model&#46; The results of the development period are consistent with the independent period&#46; In conclusion&#44; the model appears to be promising for operational applications of TC prediction for the NIO&#46;</p></span></span>"
    "textoCompletoSecciones" => array:1 [
      "secciones" => array:9 [
        0 => array:3 [
          "identificador" => "xres816087"
          "titulo" => "Resumen"
          "secciones" => array:1 [
            0 => array:1 [
              "identificador" => "abst0005"
            ]
          ]
        ]
        1 => array:3 [
          "identificador" => "xres816088"
          "titulo" => "Abstract"
          "secciones" => array:1 [
            0 => array:1 [
              "identificador" => "abst0010"
            ]
          ]
        ]
        2 => array:2 [
          "identificador" => "xpalclavsec813306"
          "titulo" => "Keywords"
        ]
        3 => array:2 [
          "identificador" => "sec0005"
          "titulo" => "Introduction"
        ]
        4 => array:3 [
          "identificador" => "sec0010"
          "titulo" => "Data and methodology"
          "secciones" => array:2 [
            0 => array:2 [
              "identificador" => "sec0015"
              "titulo" => "Procedures for selecting predictors"
            ]
            1 => array:3 [
              "identificador" => "sec0020"
              "titulo" => "Model formulation"
              "secciones" => array:2 [
                0 => array:2 [
                  "identificador" => "sec0025"
                  "titulo" => "Multiple linear regression model"
                ]
                1 => array:2 [
                  "identificador" => "sec0030"
                  "titulo" => "Neural network model"
                ]
              ]
            ]
          ]
        ]
        5 => array:3 [
          "identificador" => "sec0035"
          "titulo" => "Model evaluations"
          "secciones" => array:2 [
            0 => array:2 [
              "identificador" => "sec0040"
              "titulo" => "Model performance during the training period &#40;1971-2002&#41;"
            ]
            1 => array:2 [
              "identificador" => "sec0045"
              "titulo" => "Model performance during the testing period &#40;2003-2013&#41;"
            ]
          ]
        ]
        6 => array:2 [
          "identificador" => "sec0050"
          "titulo" => "Concluding remarks"
        ]
        7 => array:2 [
          "identificador" => "xack273907"
          "titulo" => "Acknowledgments"
        ]
        8 => array:1 [
          "titulo" => "References"
        ]
      ]
    ]
    "pdfFichero" => "main.pdf"
    "tienePdf" => true
    "fechaRecibido" => "2015-02-17"
    "fechaAceptado" => "2015-08-05"
    "PalabrasClave" => array:1 [
      "en" => array:1 [
        0 => array:4 [
          "clase" => "keyword"
          "titulo" => "Keywords"
          "identificador" => "xpalclavsec813306"
          "palabras" => array:7 [
            0 => "Tropical cyclone"
            1 => "seasonal prediction"
            2 => "neural network"
            3 => "artificial neural network"
            4 => "multiple linear regression"
            5 => "jackknife"
            6 => "north Indian Ocean"
          ]
        ]
      ]
    ]
    "tieneResumen" => true
    "resumen" => array:2 [
      "es" => array:2 [
        "titulo" => "Resumen"
        "resumen" => "<span id="abst0005" class="elsevierStyleSection elsevierViewall"><p id="spar0005" class="elsevierStyleSimplePara elsevierViewall">Se desarrolla un modelo de red neuronal para predecir el n&#250;mero estacional de ciclones tropicales &#40;CT&#41; que se desarrollan en el Oc&#233;ano &#237;ndico septentrional despu&#233;s de la estaci&#243;n del monz&#243;n &#40;octubre a diciembre&#41;&#46; Se analizan la frecuencia de los CT y las variables clim&#225;ticas de gran escala derivadas de la base de datos de rean&#225;lisis del NCEP&#47;NCAR con resoluci&#243;n de 2&#46;5<span class="elsevierStyleHsp" style=""></span>&#215;<span class="elsevierStyleHsp" style=""></span>2&#46;5&#176; para el periodo 1971-2013&#46; Se utilizaron datos del periodo 1971-2002 para desarrollar el modelo&#44; y &#233;ste se prob&#243; con datos de muestreo independientes del periodo 2003-2013&#46; Se eligieron cinco variables clim&#225;ticas de gran escala &#40;altura geopotencial a 500 hPa&#44; humedad relativa a 500 hPa&#44; presi&#243;n superficial en el mar&#44; y viento zonal a 700 y 200 hPa para el mes previo &#91;septiembre&#93;&#41; como predictores para aplicar un an&#225;lisis de correlaci&#243;n&#46; Con base en algunos par&#225;metros estad&#237;sticos de desempe&#241;o&#44; se eval&#250;a la eficacia del modelo de redes neuronales y los resultados se comparan con el modelo lineal de regresi&#243;n m&#250;ltiple&#46; Los resultados indican que el n&#250;mero de ciclones tropicales calculado por medio de ambos modelos es muy similar al n&#250;mero real de ciclones ocurridos en cada a&#241;o&#46; Sin embargo&#44; los resultados del modelo de redes neuronales fueron superiores a los del modelo linear de regresi&#243;n m&#250;ltiple&#44; de modo que esta t&#233;cnica de predicci&#243;n de ciclones tropicales puede ser muy &#250;til para prop&#243;sitos operativos de predicci&#243;n&#46;</p></span>"
      ]
      "en" => array:2 [
        "titulo" => "Abstract"
        "resumen" => "<span id="abst0010" class="elsevierStyleSection elsevierViewall"><p id="spar0010" class="elsevierStyleSimplePara elsevierViewall">A neural network &#40;NN&#41; model is developed to predict the seasonal number of tropical cyclones &#40;TCs&#41; formed over the north Indian Ocean during the post-monsoon season &#40;October&#44; November&#44; December&#41;&#46; The frequency of TCs and the large scale climate variables derived from the NCEP&#47;NCAR reanalysis dataset of resolution 2&#46;5&#176;<span class="elsevierStyleHsp" style=""></span>&#215;<span class="elsevierStyleHsp" style=""></span>2&#46;5&#176; have been analyzed for the period 1971-2013&#46; Data for the years 1971-2002 have been used for the development of the model&#44; which is tested with independent sample data for the years 2003-2013&#46; Applying correlation analysis&#44; five large-scale climate variables&#44; namely geopotential height at 500 hPa&#44; relative humidity at 500 hPa&#44; sea level pressure&#44; and zonal wind at 700 hPa and 200 hPa for the antecedent month September are selected as predictors&#46; Based on some performance parameter statistics&#44; the performance of the NN model is evaluated and the results are compared with the multiple linear regression &#40;MLR&#41; model&#46; From the results it is inferred that the predicted tropical cyclone count by both models is very close to the actual counts for both periods&#46; However&#44; the NN model is found to be superior to the MLR model&#46; This tropical cyclone prediction technique may be useful for operational prediction purposes&#46;<a name="p2"></a></p></span>"
      ]
    ]
    "multimedia" => array:12 [
      0 => array:7 [
        "identificador" => "fig0005"
        "etiqueta" => "Fig&#46; 1"
        "tipo" => "MULTIMEDIAFIGURA"
        "mostrarFloat" => true
        "mostrarDisplay" => false
        "figura" => array:1 [
          0 => array:4 [
            "imagen" => "gr1.jpeg"
            "Alto" => 503
            "Ancho" => 943
            "Tamanyo" => 50230
          ]
        ]
        "descripcion" => array:1 [
          "en" => "<p id="spar0015" class="elsevierStyleSimplePara elsevierViewall">Monthly distribution of all TCs formed over the north Indian Ocean during the period 1971-2013&#46;</p>"
        ]
      ]
      1 => array:7 [
        "identificador" => "fig0010"
        "etiqueta" => "Fig&#46; 2"
        "tipo" => "MULTIMEDIAFIGURA"
        "mostrarFloat" => true
        "mostrarDisplay" => false
        "figura" => array:1 [
          0 => array:4 [
            "imagen" => "gr2.jpeg"
            "Alto" => 582
            "Ancho" => 1142
            "Tamanyo" => 78451
          ]
        ]
        "descripcion" => array:1 [
          "en" => "<p id="spar0020" class="elsevierStyleSimplePara elsevierViewall">Distribution of TCs formed over the north Indian Ocean for the post-monsoon season during the period 1971-2013&#46;</p>"
        ]
      ]
      2 => array:7 [
        "identificador" => "fig0015"
        "etiqueta" => "Fig&#46; 3"
        "tipo" => "MULTIMEDIAFIGURA"
        "mostrarFloat" => true
        "mostrarDisplay" => false
        "figura" => array:2 [
          0 => array:1 [
            "imagen" => "gr3.jpeg"
          ]
          1 => array:1 [
            "imagen" => "gr3a.jpeg"
          ]
        ]
        "descripcion" => array:1 [
          "en" => "<p id="spar0025" class="elsevierStyleSimplePara elsevierViewall">Correlation map between seasonal TC counts and the antecedent month &#40;September&#41;&#44; &#40;a&#41; Geopotential height at 500 hPa&#44; &#40;b&#41; Relative humidity at 500 hPa&#44; &#40;c&#41; Sea level pressure&#44; The points with significant negative correlation are marked as &#8220;-&#8221; and points with positive correlation are marked as &#8220;&#43;&#8221;&#46;</p>"
        ]
      ]
      3 => array:7 [
        "identificador" => "fig0020"
        "etiqueta" => "Fig&#46; 3"
        "tipo" => "MULTIMEDIAFIGURA"
        "mostrarFloat" => true
        "mostrarDisplay" => false
        "figura" => array:1 [
          0 => array:4 [
            "imagen" => "gr4.jpeg"
            "Alto" => 734
            "Ancho" => 946
            "Tamanyo" => 97969
          ]
        ]
        "descripcion" => array:1 [
          "en" => "<p id="spar0030" class="elsevierStyleSimplePara elsevierViewall">Correlation map between seasonal TC counts and the antecedent month &#40;September&#41;&#46; &#40;d&#41; Zonal wind at 700 hPa&#46; &#40;e&#41; Zonal wind at 200 hPa&#46; The points with significant negative correlation are marked as &#8220;&#8211;&#8221; and points with positive correlation are marked as &#8220;&#43;&#8221;&#46;</p>"
        ]
      ]
      4 => array:7 [
        "identificador" => "fig0025"
        "etiqueta" => "Fig&#46; 4"
        "tipo" => "MULTIMEDIAFIGURA"
        "mostrarFloat" => true
        "mostrarDisplay" => false
        "figura" => array:1 [
          0 => array:4 [
            "imagen" => "gr5.jpeg"
            "Alto" => 614
            "Ancho" => 1474
            "Tamanyo" => 114630
          ]
        ]
        "descripcion" => array:1 [
          "en" => "<p id="spar0035" class="elsevierStyleSimplePara elsevierViewall">Three layer backpropagation neural network&#46;</p>"
        ]
      ]
      5 => array:7 [
        "identificador" => "fig0030"
        "etiqueta" => "Fig&#46; 5"
        "tipo" => "MULTIMEDIAFIGURA"
        "mostrarFloat" => true
        "mostrarDisplay" => false
        "figura" => array:1 [
          0 => array:4 [
            "imagen" => "gr6.jpeg"
            "Alto" => 561
            "Ancho" => 1572
            "Tamanyo" => 82483
          ]
        ]
        "descripcion" => array:1 [
          "en" => "<p id="spar0040" class="elsevierStyleSimplePara elsevierViewall">Time series plots for actual and predicted TC counts from the MLR and NN methods for the training period&#46; The solid line with a solid circle represents the NN predicted value&#46; The dotted line with a solid square represents the actual observation&#46; The boldface dashed line with a solid triangle represents the predicted value from the MLR model&#46;</p>"
        ]
      ]
      6 => array:7 [
        "identificador" => "fig0035"
        "etiqueta" => "Fig&#46; 6"
        "tipo" => "MULTIMEDIAFIGURA"
        "mostrarFloat" => true
        "mostrarDisplay" => false
        "figura" => array:1 [
          0 => array:4 [
            "imagen" => "gr6.jpeg"
            "Alto" => 561
            "Ancho" => 1572
            "Tamanyo" => 82483
          ]
        ]
        "descripcion" => array:1 [
          "en" => "<p id="spar0045" class="elsevierStyleSimplePara elsevierViewall">Time series plots for actual and predicted TC counts from the MLR and NN methods for the testing period&#46; The solid line with a solid circle represents the NN predicted value&#46; The dotted line with a solid square represents the actual observation&#46; The boldface dashed line with a solid triangle represents the MLR model predicted value&#46;</p>"
        ]
      ]
      7 => array:7 [
        "identificador" => "tbl0005"
        "etiqueta" => "Table I"
        "tipo" => "MULTIMEDIATABLA"
        "mostrarFloat" => true
        "mostrarDisplay" => false
        "tabla" => array:1 [
          "tablatextoimagen" => array:1 [
            0 => array:2 [
              "tabla" => array:1 [
                0 => """
                  <table border="0" frame="\n
                  \t\t\t\t\tvoid\n
                  \t\t\t\t" class=""><thead title="thead"><tr title="table-row"><th class="td" title="table-head  " align="left" valign="top" scope="col" style="border-bottom: 2px solid black">Type of disturbance&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</th><th class="td" title="table-head  " align="center" valign="top" scope="col" style="border-bottom: 2px solid black">Corresponding wind speed &#40;knots&#41;&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</th></tr></thead><tbody title="tbody"><tr title="table-row"><td class="td" title="table-entry  " align="left" valign="top">Low pressure area &#40;L&#41;&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td><td class="td" title="table-entry  " align="center" valign="top">&#60; 17&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td></tr><tr title="table-row"><td class="td" title="table-entry  " align="left" valign="top">Depression &#40;D&#41;&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td><td class="td" title="table-entry  " align="center" valign="top">17 - 27&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td></tr><tr title="table-row"><td class="td" title="table-entry  " align="left" valign="top">Deep depression &#40;DD&#41;&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td><td class="td" title="table-entry  " align="center" valign="top">28 - 33&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td></tr><tr title="table-row"><td class="td" title="table-entry  " align="left" valign="top">Cyclonic storm &#40;CS&#41;&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td><td class="td" title="table-entry  " align="center" valign="top">34 - 47&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td></tr><tr title="table-row"><td class="td" title="table-entry  " align="left" valign="top">Severe cyclonic storm &#40;SCS&#41;&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td><td class="td" title="table-entry  " align="center" valign="top">48 - 63&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td></tr><tr title="table-row"><td class="td" title="table-entry  " align="left" valign="top">Very severe cyclonic&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td><td class="td" title="table-entry  " align="" valign="top">&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td></tr><tr title="table-row"><td class="td" title="table-entry  " align="left" valign="top">storm &#40;VSCS&#41;&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td><td class="td" title="table-entry  " align="center" valign="top">64-119&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td></tr><tr title="table-row"><td class="td" title="table-entry  " align="left" valign="top">Super cyclone &#40;SC&#41;&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td><td class="td" title="table-entry  " align="center" valign="top">&#8805;120&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td></tr></tbody></table>
                  """
              ]
              "imagenFichero" => array:1 [
                0 => "xTab1371585.png"
              ]
            ]
          ]
        ]
        "descripcion" => array:1 [
          "en" => "<p id="spar0050" class="elsevierStyleSimplePara elsevierViewall">Classification of low-pressure systems according to wind speed&#46;</p>"
        ]
      ]
      8 => array:7 [
        "identificador" => "tbl0010"
        "etiqueta" => "Table II"
        "tipo" => "MULTIMEDIATABLA"
        "mostrarFloat" => true
        "mostrarDisplay" => false
        "tabla" => array:1 [
          "tablatextoimagen" => array:1 [
            0 => array:2 [
              "tabla" => array:1 [
                0 => """
                  <table border="0" frame="\n
                  \t\t\t\t\tvoid\n
                  \t\t\t\t" class=""><thead title="thead"><tr title="table-row"><th class="td" title="table-head  " align="left" valign="top" scope="col" style="border-bottom: 2px solid black">Performance parameters&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</th><th class="td" title="table-head  " align="center" valign="top" scope="col" style="border-bottom: 2px solid black">MLR&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</th><th class="td" title="table-head  " align="center" valign="top" scope="col" style="border-bottom: 2px solid black">NN&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</th></tr></thead><tbody title="tbody"><tr title="table-row"><td class="td" title="table-entry  " align="left" valign="top">Mean of actual observation &#40;<span class="elsevierStyleItalic">O</span>&#41;&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td><td class="td" title="table-entry  " align="char" valign="top">2&#46;75&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td><td class="td" title="table-entry  " align="char" valign="top">2&#46;75&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td></tr><tr title="table-row"><td class="td" title="table-entry  " align="left" valign="top">Mean of predicted variable &#40;<span class="elsevierStyleItalic">P</span>&#41;&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td><td class="td" title="table-entry  " align="char" valign="top">2&#46;81&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td><td class="td" title="table-entry  " align="char" valign="top">2&#46;63&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td></tr><tr title="table-row"><td class="td" title="table-entry  " align="left" valign="top">Standard deviation of actual observation &#40;<span class="elsevierStyleItalic">So</span>&#41;&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td><td class="td" title="table-entry  " align="char" valign="top">1&#46;21&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td><td class="td" title="table-entry  " align="char" valign="top">1&#46;21&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td></tr><tr title="table-row"><td class="td" title="table-entry  " align="left" valign="top">Standard deviation of predicted variables &#40;<span class="elsevierStyleItalic">Sp</span>&#41;&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td><td class="td" title="table-entry  " align="char" valign="top">0&#46;82&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td><td class="td" title="table-entry  " align="char" valign="top">1&#46;02&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td></tr><tr title="table-row"><td class="td" title="table-entry  " align="left" valign="top">Root mean square error &#40;RMSE&#41;&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td><td class="td" title="table-entry  " align="char" valign="top">1&#46;0&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td><td class="td" title="table-entry  " align="char" valign="top">0&#46;92&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td></tr><tr title="table-row"><td class="td" title="table-entry  " align="left" valign="top">Unsystematic root mean square error &#40;RMSE<span class="elsevierStyleInf">u</span>&#41;&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td><td class="td" title="table-entry  " align="char" valign="top">0&#46;88&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td><td class="td" title="table-entry  " align="char" valign="top">0&#46;83&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td></tr><tr title="table-row"><td class="td" title="table-entry  " align="left" valign="top">Systematic root mean square error &#40;RMSE<span class="elsevierStyleInf">s</span>&#41;&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td><td class="td" title="table-entry  " align="char" valign="top">0&#46;26&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td><td class="td" title="table-entry  " align="char" valign="top">0&#46;28&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td></tr><tr title="table-row"><td class="td" title="table-entry  " align="left" valign="top">Index of agreement &#40;<span class="elsevierStyleItalic">d</span>&#41;&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td><td class="td" title="table-entry  " align="char" valign="top">0&#46;80&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td><td class="td" title="table-entry  " align="char" valign="top">0&#46;90&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td></tr><tr title="table-row"><td class="td" title="table-entry  " align="left" valign="top">Mean absolute error &#40;MAE&#41;&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td><td class="td" title="table-entry  " align="char" valign="top">0&#46;86&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td><td class="td" title="table-entry  " align="char" valign="top">0&#46;63&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td></tr></tbody></table>
                  """
              ]
              "imagenFichero" => array:1 [
                0 => "xTab1371586.png"
              ]
            ]
          ]
        ]
        "descripcion" => array:1 [
          "en" => "<p id="spar0055" class="elsevierStyleSimplePara elsevierViewall">Performance parameters for the training period&#46;</p>"
        ]
      ]
      9 => array:7 [
        "identificador" => "tbl0015"
        "etiqueta" => "Table III"
        "tipo" => "MULTIMEDIATABLA"
        "mostrarFloat" => true
        "mostrarDisplay" => false
        "tabla" => array:1 [
          "tablatextoimagen" => array:1 [
            0 => array:2 [
              "tabla" => array:1 [
                0 => """
                  <table border="0" frame="\n
                  \t\t\t\t\tvoid\n
                  \t\t\t\t" class=""><thead title="thead"><tr title="table-row"><th class="td" title="table-head  " align="left" valign="top" scope="col" style="border-bottom: 2px solid black">Performance Parameter&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</th><th class="td" title="table-head  " align="center" valign="top" scope="col" style="border-bottom: 2px solid black">MLR&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</th><th class="td" title="table-head  " align="center" valign="top" scope="col" style="border-bottom: 2px solid black">NN&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</th></tr></thead><tbody title="tbody"><tr title="table-row"><td class="td" title="table-entry  " align="left" valign="top">Mean of actual observation &#40;<span class="elsevierStyleItalic">O</span>&#41;&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td><td class="td" title="table-entry  " align="char" valign="top">2&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td><td class="td" title="table-entry  " align="char" valign="top">2&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td></tr><tr title="table-row"><td class="td" title="table-entry  " align="left" valign="top">Mean of predicted variable &#40;<span class="elsevierStyleItalic">P</span>&#41;&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td><td class="td" title="table-entry  " align="char" valign="top">2&#46;6&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td><td class="td" title="table-entry  " align="char" valign="top">2&#46;2&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td></tr><tr title="table-row"><td class="td" title="table-entry  " align="left" valign="top">Standard deviation of actual observation <span class="elsevierStyleItalic">&#40;S</span><span class="elsevierStyleInf"><span class="elsevierStyleItalic">o</span></span><span class="elsevierStyleItalic">&#41;</span>&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td><td class="td" title="table-entry  " align="char" valign="top">0&#46;89&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td><td class="td" title="table-entry  " align="char" valign="top">0&#46;89&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td></tr><tr title="table-row"><td class="td" title="table-entry  " align="left" valign="top">Standard deviation of predicted variables &#40;<span class="elsevierStyleItalic">S</span><span class="elsevierStyleInf"><span class="elsevierStyleItalic">p</span></span>&#41;&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td><td class="td" title="table-entry  " align="char" valign="top">0&#46;60&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td><td class="td" title="table-entry  " align="char" valign="top">0&#46;77&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td></tr><tr title="table-row"><td class="td" title="table-entry  " align="left" valign="top">Root mean square error &#40;RMSE&#41;&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td><td class="td" title="table-entry  " align="char" valign="top">0&#46;94&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td><td class="td" title="table-entry  " align="char" valign="top">0&#46;51&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td></tr><tr title="table-row"><td class="td" title="table-entry  " align="left" valign="top">Unsystematic root mean square error &#40;RMSE<span class="elsevierStyleInf">u</span>&#41;&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td><td class="td" title="table-entry  " align="char" valign="top">0&#46;81&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td><td class="td" title="table-entry  " align="char" valign="top">0&#46;40&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td></tr><tr title="table-row"><td class="td" title="table-entry  " align="left" valign="top">Systematic root mean square error &#40;RMSE<span class="elsevierStyleInf">s</span>&#41;&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td><td class="td" title="table-entry  " align="char" valign="top">0&#46;19&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td><td class="td" title="table-entry  " align="char" valign="top">0&#46;32&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td></tr><tr title="table-row"><td class="td" title="table-entry  " align="left" valign="top">Index of agreement &#40;<span class="elsevierStyleItalic">d</span>&#41;&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td><td class="td" title="table-entry  " align="char" valign="top">0&#46;33&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td><td class="td" title="table-entry  " align="char" valign="top">0&#46;67&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td></tr><tr title="table-row"><td class="td" title="table-entry  " align="left" valign="top">Mean absolute error &#40;MAE&#41;&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td><td class="td" title="table-entry  " align="char" valign="top">0&#46;84&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td><td class="td" title="table-entry  " align="char" valign="top">0&#46;42&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td></tr></tbody></table>
                  """
              ]
              "imagenFichero" => array:1 [
                0 => "xTab1371587.png"
              ]
            ]
          ]
        ]
        "descripcion" => array:1 [
          "en" => "<p id="spar0060" class="elsevierStyleSimplePara elsevierViewall">Performance parameters for the testing period&#46;</p>"
        ]
      ]
      10 => array:6 [
        "identificador" => "eq0005"
        "etiqueta" => "&#40;1&#41;"
        "tipo" => "MULTIMEDIAFORMULA"
        "mostrarFloat" => false
        "mostrarDisplay" => true
        "Formula" => array:5 [
          "Matematica" => "y&#61;a0&#43;a1x1&#43;a2x2&#43;&#8943;&#43;anxn&#44;"
          "Fichero" => "STRIPIN_si1.jpeg"
          "Tamanyo" => 1810
          "Alto" => 13
          "Ancho" => 235
        ]
      ]
      11 => array:6 [
        "identificador" => "eq0010"
        "etiqueta" => "&#40;2&#41;"
        "tipo" => "MULTIMEDIAFORMULA"
        "mostrarFloat" => false
        "mostrarDisplay" => true
        "Formula" => array:5 [
          "Matematica" => "d&#61;1&#8722;&#8721;i&#61;1N&#40;Pi&#8722;Oi&#41;2&#47;&#8721;i&#61;1N&#40;Pi&#8722;O&#43;Oi&#8722;O&#175;&#41;2&#44;&#8201;&#8201;&#8201;&#8201;0&#8804;d&#8804;1MSES&#61;1N&#8201;&#8201;&#8721;i&#61;1N&#40;p&#710;i&#8722;Oi&#41;2MSEu&#61;1N&#8201;&#8201;&#8721;i&#61;1N&#40;Pi&#8722;p&#710;&#41;2"
          "Fichero" => "STRIPIN_si4.jpeg"
          "Tamanyo" => 8822
          "Alto" => 163
          "Ancho" => 446
        ]
      ]
    ]
    "bibliografia" => array:2 [
      "titulo" => "References"
      "seccion" => array:1 [
        0 => array:2 [
          "identificador" => "bibs0005"
          "bibliografiaReferencia" => array:51 [
            0 => array:3 [
              "identificador" => "bib0005"
              "etiqueta" => "Baik and Hwang&#44; 1998"
              "referencia" => array:1 [
                0 => array:2 [
                  "contribucion" => array:1 [
                    0 => array:2 [
                      "titulo" => "Tropical cyclone intensity prediction using regression method and neural network&#46;"
                      "autores" => array:1 [
                        0 => array:2 [
                          "etal" => false
                          "autores" => array:2 [
                            0 => "J&#46;J&#46; Baik"
                            1 => "H&#46;S&#46; Hwang"
                          ]
                        ]
                      ]
                    ]
                  ]
                  "host" => array:1 [
                    0 => array:1 [
                      "Revista" => array:5 [
                        "tituloSerie" => "J&#46; Meteorol&#44; Soc&#46; JPN"
                        "fecha" => "1998"
                        "volumen" => "76"
                        "paginaInicial" => "711"
                        "paginaFinal" => "717"
                      ]
                    ]
                  ]
                ]
              ]
            ]
            1 => array:3 [
              "identificador" => "bib0010"
              "etiqueta" => "Baik and Paek&#44; 2000"
              "referencia" => array:1 [
                0 => array:2 [
                  "contribucion" => array:1 [
                    0 => array:2 [
                      "titulo" => "A neural network model for predicting typhoon intensity"
                      "autores" => array:1 [
                        0 => array:2 [
                          "etal" => false
                          "autores" => array:2 [
                            0 => "J&#46;J&#46; Baik"
                            1 => "J&#46;S&#46; Paek"
                          ]
                        ]
                      ]
                    ]
                  ]
                  "host" => array:1 [
                    0 => array:1 [
                      "Revista" => array:5 [
                        "tituloSerie" => "J&#46; Meteorol&#46; Soc&#46; JPN"
                        "fecha" => "2000"
                        "volumen" => "78"
                        "paginaInicial" => "857"
                        "paginaFinal" => "869"
                      ]
                    ]
                  ]
                ]
              ]
            ]
            2 => array:3 [
              "identificador" => "bib0015"
              "etiqueta" => "Bourras et al&#46;&#44; 2003"
              "referencia" => array:1 [
                0 => array:2 [
                  "contribucion" => array:1 [
                    0 => array:2 [
                      "titulo" => "Evaluation oflatent heat flux fields from satellites and models during SEMAPHORE"
                      "autores" => array:1 [
                        0 => array:2 [
                          "etal" => false
                          "autores" => array:3 [
                            0 => "D&#46; Bourras"
                            1 => "W&#46;T&#46; Liu"
                            2 => "E&#46;W&#46; Tang"
                          ]
                        ]
                      ]
                    ]
                  ]
                  "host" => array:1 [
                    0 => array:1 [
                      "Revista" => array:5 [
                        "tituloSerie" => "J&#46; Appl&#46; Meteorol&#46;"
                        "fecha" => "2003"
                        "volumen" => "42"
                        "paginaInicial" => "227"
                        "paginaFinal" => "239"
                      ]
                    ]
                  ]
                ]
              ]
            ]
            3 => array:3 [
              "identificador" => "bib0020"
              "etiqueta" => "Chan et al&#46;&#44; 1998"
              "referencia" => array:1 [
                0 => array:2 [
                  "contribucion" => array:1 [
                    0 => array:2 [
                      "titulo" => "Seasonal forecasting of tropical cyclone activity over the western North Pacific and the South China Sea"
                      "autores" => array:1 [
                        0 => array:2 [
                          "etal" => false
                          "autores" => array:3 [
                            0 => "J&#46;C&#46;L&#46; Chan"
                            1 => "J&#46; Shi"
                            2 => "C&#46;M&#46; Lam"
                          ]
                        ]
                      ]
                    ]
                  ]
                  "host" => array:1 [
                    0 => array:1 [
                      "Revista" => array:5 [
                        "tituloSerie" => "Weather Forecast&#46;"
                        "fecha" => "1998"
                        "volumen" => "13"
                        "paginaInicial" => "997"
                        "paginaFinal" => "1004"
                      ]
                    ]
                  ]
                ]
              ]
            ]
            4 => array:3 [
              "identificador" => "bib0025"
              "etiqueta" => "Chan et al&#46;&#44; 2001"
              "referencia" => array:1 [
                0 => array:2 [
                  "contribucion" => array:1 [
                    0 => array:2 [
                      "titulo" => "Improvements in the seasonal forecasting of tropical cyclone activity over the western North Pacific"
                      "autores" => array:1 [
                        0 => array:2 [
                          "etal" => false
                          "autores" => array:3 [
                            0 => "J&#46;C&#46;L&#46; Chan"
                            1 => "J&#46; Shi"
                            2 => "K&#46;S&#46; Liu"
                          ]
                        ]
                      ]
                    ]
                  ]
                  "host" => array:1 [
                    0 => array:1 [
                      "Revista" => array:5 [
                        "tituloSerie" => "Weather Forecast&#46;"
                        "fecha" => "2001"
                        "volumen" => "16"
                        "paginaInicial" => "491"
                        "paginaFinal" => "498"
                      ]
                    ]
                  ]
                ]
              ]
            ]
            5 => array:3 [
              "identificador" => "bib0030"
              "etiqueta" => "Chase et al&#46;&#44; 2011"
              "referencia" => array:1 [
                0 => array:3 [
                  "comentario" => "D17110&#44; doi&#58;10&#46;1029&#47;2011JD015641"
                  "contribucion" => array:1 [
                    0 => array:2 [
                      "titulo" => "Projecting changes in future heavy rainfall events for Oahu Hawaii&#58; A statistical downscaling approach"
                      "autores" => array:1 [
                        0 => array:2 [
                          "etal" => false
                          "autores" => array:3 [
                            0 => "W&#46;N&#46; Chase"
                            1 => "C&#46; Pao-Shin"
                            2 => "A&#46;S&#46; Thomas"
                          ]
                        ]
                      ]
                    ]
                  ]
                  "host" => array:1 [
                    0 => array:1 [
                      "Revista" => array:3 [
                        "tituloSerie" => "J&#46; Qeophys&#46; Res&#46;"
                        "fecha" => "2011"
                        "volumen" => "116"
                      ]
                    ]
                  ]
                ]
              ]
            ]
            6 => array:3 [
              "identificador" => "bib0035"
              "etiqueta" => "Cigizoglu and Kisi&#44; 2006"
              "referencia" => array:1 [
                0 => array:2 [
                  "contribucion" => array:1 [
                    0 => array:2 [
                      "titulo" => "Methods to improve the neural network performance in suspended sediment estimation"
                      "autores" => array:1 [
                        0 => array:2 [
                          "etal" => false
                          "autores" => array:2 [
                            0 => "H&#46;K&#46; Cigizoglu"
                            1 => "O&#46; Kisi"
                          ]
                        ]
                      ]
                    ]
                  ]
                  "host" => array:1 [
                    0 => array:1 [
                      "Revista" => array:5 [
                        "tituloSerie" => "J&#46; Hydrol&#46;"
                        "fecha" => "2006"
                        "volumen" => "317"
                        "paginaInicial" => "221"
                        "paginaFinal" => "238"
                      ]
                    ]
                  ]
                ]
              ]
            ]
            7 => array:3 [
              "identificador" => "bib0040"
              "etiqueta" => "Chu and Zhao&#44; 2007"
              "referencia" => array:1 [
                0 => array:2 [
                  "contribucion" => array:1 [
                    0 => array:2 [
                      "titulo" => "A Bayesian regression approach for predicting tropical cyclone activity over the central North Pacific"
                      "autores" => array:1 [
                        0 => array:2 [
                          "etal" => false
                          "autores" => array:2 [
                            0 => "P&#46;S&#46; Chu"
                            1 => "X&#46; Zhao"
                          ]
                        ]
                      ]
                    ]
                  ]
                  "host" => array:1 [
                    0 => array:1 [
                      "Revista" => array:5 [
                        "tituloSerie" => "J&#46; Climate"
                        "fecha" => "2007"
                        "volumen" => "20"
                        "paginaInicial" => "4002"
                        "paginaFinal" => "4013"
                      ]
                    ]
                  ]
                ]
              ]
            ]
            8 => array:3 [
              "identificador" => "bib0045"
              "etiqueta" => "Chu et al&#46;&#44; 2010"
              "referencia" => array:1 [
                0 => array:3 [
                  "comentario" => "<a name="p10"></a>"
                  "contribucion" => array:1 [
                    0 => array:2 [
                      "titulo" => "Bayesian forecasting of seasonal typhoon activity&#58; A track-pattern-oriented categorization approach"
                      "autores" => array:1 [
                        0 => array:2 [
                          "etal" => false
                          "autores" => array:6 [
                            0 => "P&#46;S&#46; Chu"
                            1 => "X&#46; Zhao"
                            2 => "C&#46;H&#46; Ho"
                            3 => "H&#46;S&#46; Kim"
                            4 => "M&#46;M&#46; Lu"
                            5 => "J&#46;H&#46; Kim"
                          ]
                        ]
                      ]
                    ]
                  ]
                  "host" => array:1 [
                    0 => array:1 [
                      "Revista" => array:5 [
                        "tituloSerie" => "J&#46; Climate"
                        "fecha" => "2010"
                        "volumen" => "23"
                        "paginaInicial" => "6654"
                        "paginaFinal" => "6668"
                      ]
                    ]
                  ]
                ]
              ]
            ]
            9 => array:3 [
              "identificador" => "bib0050"
              "etiqueta" => "DeMaria et al&#46;&#44; 2001"
              "referencia" => array:1 [
                0 => array:2 [
                  "contribucion" => array:1 [
                    0 => array:2 [
                      "titulo" => "A tropical cyclone genesis parameter for the tropical Atlantic"
                      "autores" => array:1 [
                        0 => array:2 [
                          "etal" => false
                          "autores" => array:3 [
                            0 => "M&#46; DeMaria"
                            1 => "J&#46;A&#46; Knaff"
                            2 => "H&#46;C&#46; Bernadette"
                          ]
                        ]
                      ]
                    ]
                  ]
                  "host" => array:1 [
                    0 => array:1 [
                      "Revista" => array:5 [
                        "tituloSerie" => "Weather Forecast&#46;"
                        "fecha" => "2001"
                        "volumen" => "16"
                        "paginaInicial" => "219"
                        "paginaFinal" => "233"
                      ]
                    ]
                  ]
                ]
              ]
            ]
            10 => array:3 [
              "identificador" => "bib0055"
              "etiqueta" => "Dvorak&#44; 1975"
              "referencia" => array:1 [
                0 => array:2 [
                  "contribucion" => array:1 [
                    0 => array:2 [
                      "titulo" => "Tropical cyclone intensity analysis and forecasting from satellite imagery"
                      "autores" => array:1 [
                        0 => array:2 [
                          "etal" => false
                          "autores" => array:1 [
                            0 => "V&#46;F&#46; Dvorak"
                          ]
                        ]
                      ]
                    ]
                  ]
                  "host" => array:1 [
                    0 => array:1 [
                      "Revista" => array:5 [
                        "tituloSerie" => "Mon&#46; Weather Rev&#46;"
                        "fecha" => "1975"
                        "volumen" => "103"
                        "paginaInicial" => "420"
                        "paginaFinal" => "430"
                      ]
                    ]
                  ]
                ]
              ]
            ]
            11 => array:3 [
              "identificador" => "bib0060"
              "etiqueta" => "E1-Bakry&#44; 2003"
              "referencia" => array:1 [
                0 => array:2 [
                  "contribucion" => array:1 [
                    0 => array:2 [
                      "titulo" => "Feed forward neural networks modeling for K-P interactions"
                      "autores" => array:1 [
                        0 => array:2 [
                          "etal" => false
                          "autores" => array:1 [
                            0 => "M&#46;Y&#46; E1-Bakry"
                          ]
                        ]
                      ]
                    ]
                  ]
                  "host" => array:1 [
                    0 => array:1 [
                      "Revista" => array:5 [
                        "tituloSerie" => "Chaos Solitons Fract&#46;"
                        "fecha" => "2003"
                        "volumen" => "18"
                        "paginaInicial" => "995"
                        "paginaFinal" => "1000"
                      ]
                    ]
                  ]
                ]
              ]
            ]
            12 => array:3 [
              "identificador" => "bib0065"
              "etiqueta" => "Elsberry and Jeffries&#44; 1996"
              "referencia" => array:1 [
                0 => array:2 [
                  "contribucion" => array:1 [
                    0 => array:2 [
                      "titulo" => "Vertical wind shear influences on tropical cyclone formation and intensification during TCM-92 and TCM-93"
                      "autores" => array:1 [
                        0 => array:2 [
                          "etal" => false
                          "autores" => array:2 [
                            0 => "R&#46;L&#46; Elsberry"
                            1 => "R&#46; Jeffries"
                          ]
                        ]
                      ]
                    ]
                  ]
                  "host" => array:1 [
                    0 => array:1 [
                      "Revista" => array:5 [
                        "tituloSerie" => "Mon&#46; Weather&#46; Rev&#46;"
                        "fecha" => "1996"
                        "volumen" => "124"
                        "paginaInicial" => "1374"
                        "paginaFinal" => "1387"
                      ]
                    ]
                  ]
                ]
              ]
            ]
            13 => array:3 [
              "identificador" => "bib0070"
              "etiqueta" => "Elsner&#44; 2004"
              "referencia" => array:1 [
                0 => array:2 [
                  "contribucion" => array:1 [
                    0 => array:2 [
                      "titulo" => "A hierarchical Bayesian approach to seasonal hurricane modeling"
                      "autores" => array:1 [
                        0 => array:2 [
                          "etal" => false
                          "autores" => array:2 [
                            0 => "J&#46;B&#46; Elsner"
                            1 => "T&#46;H&#46; Jagger"
                          ]
                        ]
                      ]
                    ]
                  ]
                  "host" => array:1 [
                    0 => array:1 [
                      "Revista" => array:5 [
                        "tituloSerie" => "J&#46; Climate"
                        "fecha" => "2004"
                        "volumen" => "17"
                        "paginaInicial" => "2813"
                        "paginaFinal" => "2827"
                      ]
                    ]
                  ]
                ]
              ]
            ]
            14 => array:3 [
              "identificador" => "bib0075"
              "etiqueta" => "Elsner and Schmertmann&#44; 1993"
              "referencia" => array:1 [
                0 => array:2 [
                  "contribucion" => array:1 [
                    0 => array:2 [
                      "titulo" => "Improving extended range seasonal predictions of intense Atlantic hurricane activity"
                      "autores" => array:1 [
                        0 => array:2 [
                          "etal" => false
                          "autores" => array:2 [
                            0 => "J&#46;B&#46; Elsner"
                            1 => "C&#46;P&#46; Schmertmann"
                          ]
                        ]
                      ]
                    ]
                  ]
                  "host" => array:1 [
                    0 => array:1 [
                      "Revista" => array:5 [
                        "tituloSerie" => "Weather Forecast&#46;"
                        "fecha" => "1993"
                        "volumen" => "8"
                        "paginaInicial" => "345"
                        "paginaFinal" => "351"
                      ]
                    ]
                  ]
                ]
              ]
            ]
            15 => array:3 [
              "identificador" => "bib0080"
              "etiqueta" => "Elsner and Jagger&#44; 2006"
              "referencia" => array:1 [
                0 => array:2 [
                  "contribucion" => array:1 [
                    0 => array:2 [
                      "titulo" => "Prediction models for annual U&#46;S&#46; hurricane counts"
                      "autores" => array:1 [
                        0 => array:2 [
                          "etal" => false
                          "autores" => array:2 [
                            0 => "J&#46;B&#46; Elsner"
                            1 => "T&#46;H&#46; Jagger"
                          ]
                        ]
                      ]
                    ]
                  ]
                  "host" => array:1 [
                    0 => array:1 [
                      "Revista" => array:5 [
                        "tituloSerie" => "J&#46; Climate"
                        "fecha" => "2006"
                        "volumen" => "19"
                        "paginaInicial" => "2935"
                        "paginaFinal" => "2952"
                      ]
                    ]
                  ]
                ]
              ]
            ]
            16 => array:3 [
              "identificador" => "bib0085"
              "etiqueta" => "Gray&#44; 1968"
              "referencia" => array:1 [
                0 => array:2 [
                  "contribucion" => array:1 [
                    0 => array:2 [
                      "titulo" => "Global view of the origin of tropical disturbances and storms"
                      "autores" => array:1 [
                        0 => array:2 [
                          "etal" => false
                          "autores" => array:1 [
                            0 => "W&#46;M&#46; Gray"
                          ]
                        ]
                      ]
                    ]
                  ]
                  "host" => array:1 [
                    0 => array:1 [
                      "Revista" => array:5 [
                        "tituloSerie" => "Mon&#46; Weather Rev&#46;"
                        "fecha" => "1968"
                        "volumen" => "96"
                        "paginaInicial" => "669"
                        "paginaFinal" => "700"
                      ]
                    ]
                  ]
                ]
              ]
            ]
            17 => array:3 [
              "identificador" => "bib0090"
              "etiqueta" => "Gray&#44; 1977"
              "referencia" => array:1 [
                0 => array:2 [
                  "contribucion" => array:1 [
                    0 => array:2 [
                      "titulo" => "Tropical cyclone genesis in the western North Pacific"
                      "autores" => array:1 [
                        0 => array:2 [
                          "etal" => false
                          "autores" => array:1 [
                            0 => "W&#46;M&#46; Gray"
                          ]
                        ]
                      ]
                    ]
                  ]
                  "host" => array:1 [
                    0 => array:1 [
                      "Revista" => array:5 [
                        "tituloSerie" => "J&#46; Meteorol&#46; Soc&#46; JPN"
                        "fecha" => "1977"
                        "volumen" => "55"
                        "paginaInicial" => "465"
                        "paginaFinal" => "482"
                      ]
                    ]
                  ]
                ]
              ]
            ]
            18 => array:3 [
              "identificador" => "bib0095"
              "etiqueta" => "Gray&#44; 1984a"
              "referencia" => array:1 [
                0 => array:3 [
                  "comentario" => "a"
                  "contribucion" => array:1 [
                    0 => array:2 [
                      "titulo" => "Atlantic seasonal hurricane frequency&#46; Part I&#46; El Nino and 30 hPa quasi biennial oscillation influences&#46; Mon"
                      "autores" => array:1 [
                        0 => array:2 [
                          "etal" => false
                          "autores" => array:1 [
                            0 => "W&#46;M&#46; Gray"
                          ]
                        ]
                      ]
                    ]
                  ]
                  "host" => array:1 [
                    0 => array:1 [
                      "Revista" => array:5 [
                        "tituloSerie" => "Weather Rev"
                        "fecha" => "1984"
                        "volumen" => "112"
                        "paginaInicial" => "1649"
                        "paginaFinal" => "1668"
                      ]
                    ]
                  ]
                ]
              ]
            ]
            19 => array:3 [
              "identificador" => "bib0100"
              "etiqueta" => "Gray&#44; 1984b"
              "referencia" => array:1 [
                0 => array:3 [
                  "comentario" => "b"
                  "contribucion" => array:1 [
                    0 => array:2 [
                      "titulo" => "Atlantic seasonal hurricane frequency&#46; Part II&#46; Forecasting its variability&#46; Mon"
                      "autores" => array:1 [
                        0 => array:2 [
                          "etal" => false
                          "autores" => array:1 [
                            0 => "W&#46;M&#46; Gray"
                          ]
                        ]
                      ]
                    ]
                  ]
                  "host" => array:1 [
                    0 => array:1 [
                      "Revista" => array:5 [
                        "tituloSerie" => "Weather Rev"
                        "fecha" => "1984"
                        "volumen" => "112"
                        "paginaInicial" => "1669"
                        "paginaFinal" => "1683"
                      ]
                    ]
                  ]
                ]
              ]
            ]
            20 => array:3 [
              "identificador" => "bib0105"
              "etiqueta" => "Hagan and Mehnaj&#44; 1994"
              "referencia" => array:1 [
                0 => array:2 [
                  "contribucion" => array:1 [
                    0 => array:2 [
                      "titulo" => "Training feedforward networks with the Marquardt algorithm"
                      "autores" => array:1 [
                        0 => array:2 [
                          "etal" => false
                          "autores" => array:2 [
                            0 => "M&#46;T&#46; Hagan"
                            1 => "M&#46;B&#46; Mehnaj"
                          ]
                        ]
                      ]
                    ]
                  ]
                  "host" => array:1 [
                    0 => array:2 [
                      "doi" => "10.1109/72.329697"
                      "Revista" => array:6 [
                        "tituloSerie" => "IEEE Transactions on Neural Networks"
                        "fecha" => "1994"
                        "volumen" => "5"
                        "paginaInicial" => "989"
                        "paginaFinal" => "993"
                        "link" => array:1 [
                          0 => array:2 [
                            "url" => "https://www.ncbi.nlm.nih.gov/pubmed/18267874"
                            "web" => "Medline"
                          ]
                        ]
                      ]
                    ]
                  ]
                ]
              ]
            ]
            21 => array:3 [
              "identificador" => "bib0110"
              "etiqueta" => "Kim et al&#46;&#44; 2010"
              "referencia" => array:1 [
                0 => array:2 [
                  "contribucion" => array:1 [
                    0 => array:2 [
                      "titulo" => "Seasonal prediction of summertime tropical cyclone activity over the East China Sea using the least absolute deviation regression and the Poisson regression"
                      "autores" => array:1 [
                        0 => array:2 [
                          "etal" => false
                          "autores" => array:4 [
                            0 => "H&#46;S&#46; Kim"
                            1 => "H&#46;H&#46; Chang"
                            2 => "P&#46;S&#46; Chu"
                            3 => "J&#46;H&#46; Kim"
                          ]
                        ]
                      ]
                    ]
                  ]
                  "host" => array:1 [
                    0 => array:1 [
                      "Revista" => array:5 [
                        "tituloSerie" => "Int&#46; J&#46; Climatol&#46;"
                        "fecha" => "2010"
                        "volumen" => "30"
                        "paginaInicial" => "210"
                        "paginaFinal" => "219"
                      ]
                    ]
                  ]
                ]
              ]
            ]
            22 => array:3 [
              "identificador" => "bib0115"
              "etiqueta" => "Klotzbach and Philip&#44; 2008"
              "referencia" => array:1 [
                0 => array:3 [
                  "comentario" => "doi&#58;10&#46;1029&#47;2008 D 010047&#46;1-11"
                  "contribucion" => array:1 [
                    0 => array:2 [
                      "titulo" => "Refinement to Atlantic basin seasonal hurricane prediction from 1 December"
                      "autores" => array:1 [
                        0 => array:2 [
                          "etal" => false
                          "autores" => array:2 [
                            0 => "J&#46; Klotzbach"
                            1 => "J&#46; Philip"
                          ]
                        ]
                      ]
                    ]
                  ]
                  "host" => array:1 [
                    0 => array:1 [
                      "Revista" => array:4 [
                        "tituloSerie" => "J&#46; Geophys&#46; Res&#46;"
                        "fecha" => "2008"
                        "volumen" => "113"
                        "paginaInicial" => "D17109"
                      ]
                    ]
                  ]
                ]
              ]
            ]
            23 => array:3 [
              "identificador" => "bib0120"
              "etiqueta" => "Kotal et al&#46;&#44; 2008"
              "referencia" => array:1 [
                0 => array:2 [
                  "contribucion" => array:1 [
                    0 => array:2 [
                      "titulo" => "A statistical cyclone intensity prediction &#40;SCIP&#41; model for Bay of Bengal"
                      "autores" => array:1 [
                        0 => array:2 [
                          "etal" => false
                          "autores" => array:4 [
                            0 => "S&#46;D&#46; Kotal"
                            1 => "S&#46;K&#46; Roy Bhowmik"
                            2 => "P&#46;K&#46; Kundu"
                            3 => "A&#46;K&#46; Das"
                          ]
                        ]
                      ]
                    ]
                  ]
                  "host" => array:1 [
                    0 => array:1 [
                      "Revista" => array:5 [
                        "tituloSerie" => "J&#46; Earth Syst&#46; Sci&#46;"
                        "fecha" => "2008"
                        "volumen" => "117"
                        "paginaInicial" => "157"
                        "paginaFinal" => "168"
                      ]
                    ]
                  ]
                ]
              ]
            ]
            24 => array:3 [
              "identificador" => "bib0125"
              "etiqueta" => "Kotal et al&#46;&#44; 2009"
              "referencia" => array:1 [
                0 => array:2 [
                  "contribucion" => array:1 [
                    0 => array:2 [
                      "titulo" => "Analysis of cyclogenesis parameter for developing and nondeveloping low-pressure systems over the Indian Sea"
                      "autores" => array:1 [
                        0 => array:2 [
                          "etal" => false
                          "autores" => array:3 [
                            0 => "S&#46;D&#46; Kotal"
                            1 => "P&#46;K&#46; Kundu"
                            2 => "S&#46;K&#46; Roy Bhowmik"
                          ]
                        ]
                      ]
                    ]
                  ]
                  "host" => array:1 [
                    0 => array:1 [
                      "Revista" => array:5 [
                        "tituloSerie" => "Nat&#46; Hazards"
                        "fecha" => "2009"
                        "volumen" => "50"
                        "paginaInicial" => "389"
                        "paginaFinal" => "402"
                      ]
                    ]
                  ]
                ]
              ]
            ]
            25 => array:3 [
              "identificador" => "bib0130"
              "etiqueta" => "Kuligowski and Barros&#44; 1998"
              "referencia" => array:1 [
                0 => array:2 [
                  "contribucion" => array:1 [
                    0 => array:2 [
                      "titulo" => "Experiments in short-term precipitation forecasting using artificial neutral networks"
                      "autores" => array:1 [
                        0 => array:2 [
                          "etal" => false
                          "autores" => array:2 [
                            0 => "R&#46;J&#46; Kuligowski"
                            1 => "A&#46;P&#46; Barros"
                          ]
                        ]
                      ]
                    ]
                  ]
                  "host" => array:1 [
                    0 => array:1 [
                      "Revista" => array:5 [
                        "tituloSerie" => "Month Weather Rev&#46;"
                        "fecha" => "1998"
                        "volumen" => "126"
                        "paginaInicial" => "470"
                        "paginaFinal" => "482"
                      ]
                    ]
                  ]
                ]
              ]
            ]
            26 => array:3 [
              "identificador" => "bib0135"
              "etiqueta" => "Lehmiller et al&#46;&#44; 1997"
              "referencia" => array:1 [
                0 => array:2 [
                  "contribucion" => array:1 [
                    0 => array:2 [
                      "titulo" => "Seasonal prediction models for North Atlantic basin hurricane location"
                      "autores" => array:1 [
                        0 => array:2 [
                          "etal" => false
                          "autores" => array:3 [
                            0 => "G&#46;S&#46; Lehmiller"
                            1 => "T&#46;B&#46; Kimberlain"
                            2 => "J&#46;B&#46; Elsner"
                          ]
                        ]
                      ]
                    ]
                  ]
                  "host" => array:1 [
                    0 => array:1 [
                      "Revista" => array:5 [
                        "tituloSerie" => "Mon&#46; Weather Rev&#46;"
                        "fecha" => "1997"
                        "volumen" => "125"
                        "paginaInicial" => "1780"
                        "paginaFinal" => "1791"
                      ]
                    ]
                  ]
                ]
              ]
            ]
            27 => array:3 [
              "identificador" => "bib0140"
              "etiqueta" => "Liu and Chan&#44; 2003"
              "referencia" => array:1 [
                0 => array:2 [
                  "contribucion" => array:1 [
                    0 => array:2 [
                      "titulo" => "Climatological characteristics and seasonal forecasting of tropical cyclones making landfall along the South China coast"
                      "autores" => array:1 [
                        0 => array:2 [
                          "etal" => false
                          "autores" => array:2 [
                            0 => "K&#46;S&#46; Liu"
                            1 => "J&#46;C&#46;L&#46; Chan"
                          ]
                        ]
                      ]
                    ]
                  ]
                  "host" => array:1 [
                    0 => array:1 [
                      "Revista" => array:5 [
                        "tituloSerie" => "Mon&#46; Weather Rev&#46;"
                        "fecha" => "2003"
                        "volumen" => "131"
                        "paginaInicial" => "1650"
                        "paginaFinal" => "1662"
                      ]
                    ]
                  ]
                ]
              ]
            ]
            28 => array:3 [
              "identificador" => "bib0145"
              "etiqueta" => "Lu et al&#46;&#44; 2010"
              "referencia" => array:1 [
                0 => array:2 [
                  "contribucion" => array:1 [
                    0 => array:2 [
                      "titulo" => "Seasonal prediction of tropical cyclone activity in the vicinity of Taiwan using the Bayesian multivariate regression method"
                      "autores" => array:1 [
                        0 => array:2 [
                          "etal" => false
                          "autores" => array:3 [
                            0 => "M&#46;M&#46; Lu"
                            1 => "P&#46;S&#46; Chu"
                            2 => "Y&#46;C&#46; Lin"
                          ]
                        ]
                      ]
                    ]
                  ]
                  "host" => array:1 [
                    0 => array:1 [
                      "Revista" => array:5 [
                        "tituloSerie" => "Weather Forecast&#46;"
                        "fecha" => "2010"
                        "volumen" => "25"
                        "paginaInicial" => "1780"
                        "paginaFinal" => "1795"
                      ]
                    ]
                  ]
                ]
              ]
            ]
            29 => array:3 [
              "identificador" => "bib0150"
              "etiqueta" => "Marquardt&#44; 1963"
              "referencia" => array:1 [
                0 => array:2 [
                  "contribucion" => array:1 [
                    0 => array:2 [
                      "titulo" => "An algorithm for least-squares estimation of non-linear parameters"
                      "autores" => array:1 [
                        0 => array:2 [
                          "etal" => false
                          "autores" => array:1 [
                            0 => "D&#46;W&#46; Marquardt"
                          ]
                        ]
                      ]
                    ]
                  ]
                  "host" => array:1 [
                    0 => array:1 [
                      "Revista" => array:5 [
                        "tituloSerie" => "J&#46; Soc&#46; Ind&#46; Appl&#46; Math&#46;"
                        "fecha" => "1963"
                        "volumen" => "11"
                        "paginaInicial" => "431"
                        "paginaFinal" => "441"
                      ]
                    ]
                  ]
                ]
              ]
            ]
            30 => array:3 [
              "identificador" => "bib0155"
              "etiqueta" => "Maqsood et al&#46;&#44; 2002"
              "referencia" => array:1 [
                0 => array:2 [
                  "contribucion" => array:1 [
                    0 => array:2 [
                      "titulo" => "Intelligent weather monitoring systems using connectionist models&#46;"
                      "autores" => array:1 [
                        0 => array:2 [
                          "etal" => false
                          "autores" => array:3 [
                            0 => "I&#46; Maqsood"
                            1 => "M&#46;R&#46; Khan"
                            2 => "A&#46; Abraham"
                          ]
                        ]
                      ]
                    ]
                  ]
                  "host" => array:1 [
                    0 => array:2 [
                      "doi" => "10.1113/JP273094"
                      "Revista" => array:6 [
                        "tituloSerie" => "Neural&#44; Parallel &#38; Scientific Computations"
                        "fecha" => "2002"
                        "volumen" => "10"
                        "paginaInicial" => "157"
                        "paginaFinal" => "178"
                        "link" => array:1 [
                          0 => array:2 [
                            "url" => "https://www.ncbi.nlm.nih.gov/pubmed/28295377"
                            "web" => "Medline"
                          ]
                        ]
                      ]
                    ]
                  ]
                ]
              ]
            ]
            31 => array:3 [
              "identificador" => "bib0160"
              "etiqueta" => "McCam&#44; 1992"
              "referencia" => array:1 [
                0 => array:2 [
                  "contribucion" => array:1 [
                    0 => array:2 [
                      "titulo" => "A neural network short-term forecast of significant thunderstorm"
                      "autores" => array:1 [
                        0 => array:2 [
                          "etal" => false
                          "autores" => array:1 [
                            0 => "D&#46;W&#46; McCam"
                          ]
                        ]
                      ]
                    ]
                  ]
                  "host" => array:1 [
                    0 => array:1 [
                      "Revista" => array:5 [
                        "tituloSerie" => "Weather Forecast&#46;"
                        "fecha" => "1992"
                        "volumen" => "7"
                        "paginaInicial" => "525"
                        "paginaFinal" => "534"
                      ]
                    ]
                  ]
                ]
              ]
            ]
            32 => array:3 [
              "identificador" => "bib0165"
              "etiqueta" => "Mitra et al&#46;&#44; 2010"
              "referencia" => array:1 [
                0 => array:2 [
                  "contribucion" => array:1 [
                    0 => array:2 [
                      "titulo" => "A neural network approach for temperature retrieval from AMSU-A measurements onboard NOAA-15 and NOAA-16 satellites and a case study during Gonu cyclone"
                      "autores" => array:1 [
                        0 => array:2 [
                          "etal" => false
                          "autores" => array:4 [
                            0 => "A&#46;K&#46; Mitra"
                            1 => "P&#46;K&#46; Kundu"
                            2 => "A&#46;K&#46; Sharma"
                            3 => "S&#46;K&#46; Roy Bhowmik"
                          ]
                        ]
                      ]
                    ]
                  ]
                  "host" => array:1 [
                    0 => array:1 [
                      "Revista" => array:5 [
                        "tituloSerie" => "Atmosfera"
                        "fecha" => "2010"
                        "volumen" => "23"
                        "paginaInicial" => "225"
                        "paginaFinal" => "239"
                      ]
                    ]
                  ]
                ]
              ]
            ]
            33 => array:3 [
              "identificador" => "bib0170"
              "etiqueta" => "Nath et al&#46;&#44; 2013"
              "referencia" => array:1 [
                0 => array:2 [
                  "contribucion" => array:1 [
                    0 => array:2 [
                      "titulo" => "Analysis of a genesis potential parameter during pre-cyclone watch period over the Bay of Bengal"
                      "autores" => array:1 [
                        0 => array:2 [
                          "etal" => false
                          "autores" => array:3 [
                            0 => "S&#46; Nath"
                            1 => "S&#46;D&#46; Kotal"
                            2 => "P&#46;K&#46; Kundu"
                          ]
                        ]
                      ]
                    ]
                  ]
                  "host" => array:1 [
                    0 => array:1 [
                      "Revista" => array:5 [
                        "tituloSerie" => "Nat&#46; Hazards"
                        "fecha" => "2013"
                        "volumen" => "65"
                        "paginaInicial" => "2253"
                        "paginaFinal" => "2265"
                      ]
                    ]
                  ]
                ]
              ]
            ]
            34 => array:3 [
              "identificador" => "bib0175"
              "etiqueta" => "Nicholls&#44; 1979"
              "referencia" => array:1 [
                0 => array:2 [
                  "contribucion" => array:1 [
                    0 => array:2 [
                      "titulo" => "A possible method for predicting seasonal tropical cyclone activity in the Australian region"
                      "autores" => array:1 [
                        0 => array:2 [
                          "etal" => false
                          "autores" => array:1 [
                            0 => "N&#46; Nicholls"
                          ]
                        ]
                      ]
                    ]
                  ]
                  "host" => array:1 [
                    0 => array:1 [
                      "Revista" => array:5 [
                        "tituloSerie" => "Mon&#46; Weather Rev"
                        "fecha" => "1979"
                        "volumen" => "107"
                        "paginaInicial" => "1221"
                        "paginaFinal" => "1224"
                      ]
                    ]
                  ]
                ]
              ]
            ]
            35 => array:3 [
              "identificador" => "bib0180"
              "etiqueta" => "Norton et al&#46;&#44; 2011"
              "referencia" => array:1 [
                0 => array:3 [
                  "comentario" => "doi&#58;10&#46;1029&#47;2011JD015641"
                  "contribucion" => array:1 [
                    0 => array:2 [
                      "titulo" => "Estimating changes in future heavy rainfall events for Oahu Hawaii&#58; A statistical downscaling approach"
                      "autores" => array:1 [
                        0 => array:2 [
                          "etal" => false
                          "autores" => array:3 [
                            0 => "C&#46; Norton"
                            1 => "P&#46;S&#46; Chu"
                            2 => "T&#46;A&#46; Schroeder"
                          ]
                        ]
                      ]
                    ]
                  ]
                  "host" => array:1 [
                    0 => array:1 [
                      "Revista" => array:4 [
                        "tituloSerie" => "J&#46; Geophys&#46; Res&#46;-Atmos"
                        "fecha" => "2011"
                        "volumen" => "116"
                        "paginaInicial" => "D17110"
                      ]
                    ]
                  ]
                ]
              ]
            ]
            36 => array:3 [
              "identificador" => "bib0185"
              "etiqueta" => "Palmen&#44; 1948"
              "referencia" => array:1 [
                0 => array:2 [
                  "contribucion" => array:1 [
                    0 => array:2 [
                      "titulo" => "On the formation and structure of the tropical hurricane"
                      "autores" => array:1 [
                        0 => array:2 [
                          "etal" => false
                          "autores" => array:1 [
                            0 => "E&#46;N&#46; Palmen"
                          ]
                        ]
                      ]
                    ]
                  ]
                  "host" => array:1 [
                    0 => array:1 [
                      "Revista" => array:5 [
                        "tituloSerie" => "Geophysica"
                        "fecha" => "1948"
                        "volumen" => "3"
                        "paginaInicial" => "26"
                        "paginaFinal" => "38"
                      ]
                    ]
                  ]
                ]
              ]
            ]
            37 => array:3 [
              "identificador" => "bib0190"
              "etiqueta" => "Pozzi et al&#46;&#44; 2000"
              "referencia" => array:1 [
                0 => array:3 [
                  "comentario" => "<a name="p11"></a>"
                  "contribucion" => array:1 [
                    0 => array:2 [
                      "titulo" => "Sea surface temperature and isotopic reconstruction from nannoplankton data using artificial neural networks"
                      "autores" => array:1 [
                        0 => array:2 [
                          "etal" => false
                          "autores" => array:3 [
                            0 => "M&#46; Pozzi"
                            1 => "B&#46;A&#46; Malmgren"
                            2 => "S&#46; Monechi"
                          ]
                        ]
                      ]
                    ]
                  ]
                  "host" => array:1 [
                    0 => array:1 [
                      "Revista" => array:5 [
                        "tituloSerie" => "Palaeontol&#46; Electron&#46;"
                        "fecha" => "2000"
                        "volumen" => "3"
                        "paginaInicial" => "4"
                        "paginaFinal" => "14"
                      ]
                    ]
                  ]
                ]
              ]
            ]
            38 => array:3 [
              "identificador" => "bib0195"
              "etiqueta" => "Ram&#237;rez and Veneros&#44; 2004"
              "referencia" => array:1 [
                0 => array:3 [
                  "comentario" => "May"
                  "contribucion" => array:1 [
                    0 => array:2 [
                      "titulo" => "Upper air information and neural networks to estimate hurricane intensity&#46; 26th Conference on Hurricanes and Tropical Meteorology"
                      "autores" => array:1 [
                        0 => array:2 [
                          "etal" => false
                          "autores" => array:2 [
                            0 => "N&#46;D&#46; Ram&#237;rez"
                            1 => "A&#46; Veneros"
                          ]
                        ]
                      ]
                    ]
                  ]
                  "host" => array:1 [
                    0 => array:1 [
                      "Libro" => array:5 [
                        "fecha" => "2004"
                        "paginaInicial" => "2"
                        "paginaFinal" => "7"
                        "editorial" => "American Meteorological Society"
                        "editorialLocalizacion" => "Miami"
                      ]
                    ]
                  ]
                ]
              ]
            ]
            39 => array:3 [
              "identificador" => "bib0200"
              "etiqueta" => "Ram&#237;rez and Castro&#44; 2006"
              "referencia" => array:1 [
                0 => array:3 [
                  "comentario" => "April"
                  "contribucion" => array:1 [
                    0 => array:2 [
                      "titulo" => "A transfer function model to predict hurricane intensity&#46; 27th Conference on Hurricanes and Tropical Meteorology"
                      "autores" => array:1 [
                        0 => array:2 [
                          "etal" => false
                          "autores" => array:2 [
                            0 => "N&#46;D&#46; Ram&#237;rez"
                            1 => "J&#46;M&#46; Castro"
                          ]
                        ]
                      ]
                    ]
                  ]
                  "host" => array:1 [
                    0 => array:1 [
                      "Libro" => array:5 [
                        "fecha" => "2006"
                        "paginaInicial" => "23"
                        "paginaFinal" => "28"
                        "editorial" => "American Meteorological Society"
                        "editorialLocalizacion" => "Monterey&#44; Ca"
                      ]
                    ]
                  ]
                ]
              ]
            ]
            40 => array:3 [
              "identificador" => "bib0205"
              "etiqueta" => "Richaume et al&#46;&#44; 2000"
              "referencia" => array:1 [
                0 => array:2 [
                  "contribucion" => array:1 [
                    0 => array:2 [
                      "titulo" => "Neural network wind retrieval from ERS-1 scatterometer data"
                      "autores" => array:1 [
                        0 => array:2 [
                          "etal" => false
                          "autores" => array:6 [
                            0 => "P&#46; Richaume"
                            1 => "F&#46; Badran"
                            2 => "M&#46; Crepon"
                            3 => "C&#46; Mejia"
                            4 => "H&#46; Roquet"
                            5 => "S&#46; Thiria"
                          ]
                        ]
                      ]
                    ]
                  ]
                  "host" => array:1 [
                    0 => array:1 [
                      "Revista" => array:5 [
                        "tituloSerie" => "J&#46; Qeophys&#46; Res&#46;"
                        "fecha" => "2000"
                        "volumen" => "105"
                        "paginaInicial" => "8737"
                        "paginaFinal" => "8751"
                      ]
                    ]
                  ]
                ]
              ]
            ]
            41 => array:3 [
              "identificador" => "bib0210"
              "etiqueta" => "Roy Bhowmik&#44; 2003"
              "referencia" => array:1 [
                0 => array:2 [
                  "contribucion" => array:1 [
                    0 => array:2 [
                      "titulo" => "An evaluation of cyclone genesis parameter over the Bay of Bengal using modal analysis"
                      "autores" => array:1 [
                        0 => array:2 [
                          "etal" => false
                          "autores" => array:1 [
                            0 => "S&#46;K&#46; Roy Bhowmik"
                          ]
                        ]
                      ]
                    ]
                  ]
                  "host" => array:1 [
                    0 => array:1 [
                      "Revista" => array:5 [
                        "tituloSerie" => "Mausam"
                        "fecha" => "2003"
                        "volumen" => "54"
                        "paginaInicial" => "351"
                        "paginaFinal" => "358"
                      ]
                    ]
                  ]
                ]
              ]
            ]
            42 => array:3 [
              "identificador" => "bib0215"
              "etiqueta" => "Roy Bhowmik et al&#46;&#44; 2007"
              "referencia" => array:1 [
                0 => array:2 [
                  "contribucion" => array:1 [
                    0 => array:2 [
                      "titulo" => "An empirical model for predicting intensity of tropical cyclone over the Bay of Bengal"
                      "autores" => array:1 [
                        0 => array:2 [
                          "etal" => false
                          "autores" => array:3 [
                            0 => "S&#46;K&#46; Roy Bhowmik"
                            1 => "S&#46;D&#46; Kotal"
                            2 => "S&#46;R&#46; Kalsi"
                          ]
                        ]
                      ]
                    ]
                  ]
                  "host" => array:1 [
                    0 => array:1 [
                      "Revista" => array:5 [
                        "tituloSerie" => "Nat&#46; Hazards"
                        "fecha" => "2007"
                        "volumen" => "41"
                        "paginaInicial" => "447"
                        "paginaFinal" => "455"
                      ]
                    ]
                  ]
                ]
              ]
            ]
            43 => array:3 [
              "identificador" => "bib0220"
              "etiqueta" => "Schroeder et al&#46;&#44; 2002"
              "referencia" => array:1 [
                0 => array:2 [
                  "contribucion" => array:1 [
                    0 => array:2 [
                      "titulo" => "Artificial-neural network- based atmospheric correction algorithm&#58; Application to MERIS data"
                      "autores" => array:1 [
                        0 => array:2 [
                          "etal" => false
                          "autores" => array:4 [
                            0 => "T&#46; Schroeder"
                            1 => "J&#46; Fischer"
                            2 => "M&#46; Schaale"
                            3 => "F&#46; Fell"
                          ]
                        ]
                      ]
                    ]
                  ]
                  "host" => array:1 [
                    0 => array:1 [
                      "Revista" => array:5 [
                        "tituloSerie" => "Proc&#46; SPIE&#46; Int&#46; Soc&#46; Opt&#46; Eng&#46;"
                        "fecha" => "2002"
                        "volumen" => "4892"
                        "paginaInicial" => "124"
                        "paginaFinal" => "132"
                      ]
                    ]
                  ]
                ]
              ]
            ]
            44 => array:3 [
              "identificador" => "bib0225"
              "etiqueta" => "Ustaoglu et al&#46;&#44; 2008"
              "referencia" => array:1 [
                0 => array:2 [
                  "contribucion" => array:1 [
                    0 => array:2 [
                      "titulo" => "Forecast of daily mean&#44; maximum and minimum temperature time series by three artificial neural network methods"
                      "autores" => array:1 [
                        0 => array:2 [
                          "etal" => false
                          "autores" => array:3 [
                            0 => "B&#46; Ustaoglu"
                            1 => "H&#46;K&#46; Cigizoglu"
                            2 => "M&#46; Karaca"
                          ]
                        ]
                      ]
                    ]
                  ]
                  "host" => array:1 [
                    0 => array:1 [
                      "Revista" => array:5 [
                        "tituloSerie" => "Meteorol&#46; Appl&#46;"
                        "fecha" => "2008"
                        "volumen" => "15"
                        "paginaInicial" => "431"
                        "paginaFinal" => "445"
                      ]
                    ]
                  ]
                ]
              ]
            ]
            45 => array:3 [
              "identificador" => "bib0230"
              "etiqueta" => "Vos et al&#46;&#44; 2009"
              "referencia" => array:1 [
                0 => array:1 [
                  "referenciaCompleta" => "Vos F&#46;&#44; J&#46; Rodriguez&#44; R&#46; Below and D&#46; Guha-Sapir&#44; 2009&#46; Annual disaster statistical review 2008&#46; Centre for Research on the Epidemiology of Disasters &#40;CRED&#41;&#44; Brussels&#44; Belgium&#44; 33 pp&#46; Available at&#58; <a href="http://www.cred.be/sites/default/files/ADSR_2009.pdf">http&#58;&#47;&#47;www&#46;cred&#46;be&#47;sites&#47;default&#47;files&#47;ADSR&#95;2009&#46;pdf</a>&#46;"
                ]
              ]
            ]
            46 => array:3 [
              "identificador" => "bib0235"
              "etiqueta" => "Watterson et al&#46;&#44; 1995"
              "referencia" => array:1 [
                0 => array:2 [
                  "contribucion" => array:1 [
                    0 => array:2 [
                      "titulo" => "Seasonal and interannual variability of tropical cyclogenesis&#58; diagnostics from large-scale fields"
                      "autores" => array:1 [
                        0 => array:2 [
                          "etal" => false
                          "autores" => array:3 [
                            0 => "I&#46;G&#46; Watterson"
                            1 => "J&#46;L&#46; Evans"
                            2 => "B&#46;F&#46; Ryan"
                          ]
                        ]
                      ]
                    ]
                  ]
                  "host" => array:1 [
                    0 => array:1 [
                      "Revista" => array:5 [
                        "tituloSerie" => "J&#46; Climate"
                        "fecha" => "1995"
                        "volumen" => "8"
                        "paginaInicial" => "3052"
                        "paginaFinal" => "3066"
                      ]
                    ]
                  ]
                ]
              ]
            ]
            47 => array:3 [
              "identificador" => "bib0240"
              "etiqueta" => "Werner and Holbrook&#44; 2011"
              "referencia" => array:1 [
                0 => array:2 [
                  "contribucion" => array:1 [
                    0 => array:2 [
                      "titulo" => "A Bayesian forecast model of Australian region tropical cyclone formation"
                      "autores" => array:1 [
                        0 => array:2 [
                          "etal" => false
                          "autores" => array:2 [
                            0 => "A&#46; Werner"
                            1 => "N&#46;J&#46; Holbrook"
                          ]
                        ]
                      ]
                    ]
                  ]
                  "host" => array:1 [
                    0 => array:1 [
                      "Revista" => array:5 [
                        "tituloSerie" => "J Climate"
                        "fecha" => "2011"
                        "volumen" => "24"
                        "paginaInicial" => "6114"
                        "paginaFinal" => "6131"
                      ]
                    ]
                  ]
                ]
              ]
            ]
            48 => array:3 [
              "identificador" => "bib0245"
              "etiqueta" => "Willmott&#44; 1982"
              "referencia" => array:1 [
                0 => array:2 [
                  "contribucion" => array:1 [
                    0 => array:2 [
                      "titulo" => "Some comments on the evaluation of model performance"
                      "autores" => array:1 [
                        0 => array:2 [
                          "etal" => false
                          "autores" => array:1 [
                            0 => "C&#46;J&#46; Willmott"
                          ]
                        ]
                      ]
                    ]
                  ]
                  "host" => array:1 [
                    0 => array:1 [
                      "Revista" => array:5 [
                        "tituloSerie" => "B&#46; Am&#46; Meteorol&#46; Soc&#46;"
                        "fecha" => "1982"
                        "volumen" => "63"
                        "paginaInicial" => "1309"
                        "paginaFinal" => "1313"
                      ]
                    ]
                  ]
                ]
              ]
            ]
            49 => array:3 [
              "identificador" => "bib0250"
              "etiqueta" => "WMO&#44; 2014"
              "referencia" => array:1 [
                0 => array:1 [
                  "referenciaCompleta" => "WMO&#44; 2014&#46; Tropical cyclone operational plan for the Bay of Bengal and the Arabian Sea&#46; Technical document WMO&#47;TD No&#46; 84&#46; &#40;Tropical Cyclone Programme Report No&#46; TCP-21&#46;&#41; World Meteorological Organization&#44; Geneva&#46; Available at&#58; <a href="http://www.wmo.int/pages//prog/www/tcp/documents/TCP-21Edition2014_final.pdf">www&#46;wmo&#46;int&#47;pages&#47;&#47;prog&#47;www&#47;tcp&#47;documents&#47;TCP-21Edition2014&#95;final&#46;pdf</a>&#46;"
                ]
              ]
            ]
            50 => array:3 [
              "identificador" => "bib0255"
              "etiqueta" => "Young&#44; 2006"
              "referencia" => array:1 [
                0 => array:3 [
                  "comentario" => "doi&#58;10&#46;1029&#47;2006JC003540"
                  "contribucion" => array:1 [
                    0 => array:2 [
                      "titulo" => "Directional spectra of hurricane wind waves"
                      "autores" => array:1 [
                        0 => array:2 [
                          "etal" => false
                          "autores" => array:1 [
                            0 => "I&#46;R&#46; Young"
                          ]
                        ]
                      ]
                    ]
                  ]
                  "host" => array:1 [
                    0 => array:1 [
                      "Revista" => array:4 [
                        "tituloSerie" => "J&#46; Qeophys&#46; Res&#46;"
                        "fecha" => "2006"
                        "volumen" => "111"
                        "paginaInicial" => "C08020"
                      ]
                    ]
                  ]
                ]
              ]
            ]
          ]
        ]
      ]
    ]
    "agradecimientos" => array:1 [
      0 => array:4 [
        "identificador" => "xack273907"
        "titulo" => "Acknowledgments"
        "texto" => "<p id="par0130" class="elsevierStylePara elsevierViewall">The authors are grateful to the Director General of Meteorology&#44; India Meteorological Department&#44; New Delhi for providing all the facilities to carry out this research work&#46; The authors acknowledge the use of NCEP data in this research work&#46; Authors are also grateful with the anonymous reviewers for their suggestions for improving the paper&#46;</p>"
        "vista" => "all"
      ]
    ]
  ]
  "idiomaDefecto" => "en"
  "url" => "/01876236/0000002800000004/v1_201703180150/S0187623617300115/v1_201703180150/en/main.assets"
  "Apartado" => null
  "PDF" => "https://static.elsevier.es/multimedia/01876236/0000002800000004/v1_201703180150/S0187623617300115/v1_201703180150/en/main.pdf?idApp=UINPBA00004N&text.app=https://www.elsevier.es/"
  "EPUB" => "https://multimedia.elsevier.es/PublicationsMultimediaV1/item/epub/S0187623617300115?idApp=UINPBA00004N"
]

Article information

ISSN: 01876236
Original language: English

DOI:10.20937/ATM.2015.28.04.06

The statistics are updated each day

Year/Month	Html	Pdf	Total

2024 November	1	1	2
2024 October	52	11	63
2024 September	62	19	81
2024 August	37	16	53
2024 July	20	3	23
2024 June	29	8	37
2024 May	34	10	44
2024 April	29	4	33
2024 March	39	4	43
2024 February	58	6	64
2024 January	87	7	94
2023 December	52	13	65
2023 November	67	11	78
2023 October	68	15	83
2023 September	53	11	64
2023 August	38	13	51
2023 July	51	4	55
2023 June	56	2	58
2023 May	67	8	75
2023 April	71	4	75
2023 March	72	3	75
2023 February	47	4	51
2023 January	42	4	46
2022 December	47	7	54
2022 November	26	7	33
2022 October	28	13	41
2022 September	37	11	48
2022 August	36	7	43
2022 July	22	10	32
2022 June	37	7	44
2022 May	36	4	40
2022 April	34	5	39
2022 March	68	15	83
2022 February	97	8	105
2022 January	97	6	103
2021 December	42	8	50
2021 November	67	10	77
2021 October	65	12	77
2021 September	58	11	69
2021 August	38	14	52
2021 July	31	13	44
2021 June	26	11	37
2021 May	20	9	29
2021 April	81	17	98
2021 March	28	8	36
2021 February	7	3	10
2021 January	16	9	25
2020 December	18	4	22
2020 November	12	10	22
2020 October	11	5	16
2020 September	15	7	22
2020 August	18	10	28
2020 July	11	2	13
2020 June	6	3	9
2020 May	14	1	15
2020 April	4	2	6
2020 March	8	3	11
2020 February	11	2	13
2020 January	11	6	17
2019 December	8	8	16
2019 November	8	5	13
2019 October	10	0	10
2019 September	9	6	15
2019 August	5	0	5
2019 July	7	3	10
2019 June	14	11	25
2019 May	49	44	93
2019 April	27	18	45
2019 March	2	2	4
2019 February	6	3	9
2019 January	8	3	11
2018 December	8	1	9
2018 November	12	0	12
2018 October	5	6	11
2018 September	0	6	6
2018 August	12	0	12
2018 July	10	1	11
2018 June	14	2	16
2018 May	90	4	94
2018 April	22	1	23
2018 January	1	0	1
2017 December	4	0	4
2017 November	2	1	3
2017 October	3	0	3
2017 September	10	2	12
2017 August	2	1	3
2017 July	1	0	1
2017 June	3	1	4
2017 May	2	0	2
2017 April	1	1	2
2017 March	2	1	3

Show all

Indexed in:

Follow us:

Statistics

Indexed in:

Follow us:

Statistics

Subscribe to our newsletter