Modelado de series climatológicas mediante una red neuronal artificial

Jesús Palazón González; Adela García Guzmán

doi:10.4995/ia.2004.2521

Autores/as

Jesús Palazón González Universidad de Córdoba
Adela García Guzmán Universidad de Córdoba

DOI:

https://doi.org/10.4995/ia.2004.2521

Palabras clave:

Intensidad de la lluvia, Dependencia de la intensidad y duración de la lluvia, Red neuronal artificial, Términos de error en una red neuronal artificial

Resumen

Se ha desarrollado un modelo de red neuronal para caracterizar series meteorológicas que son difíciles de modelar con los métodos clásicos de inferencia estadística. Concretamente, se ha utilizado la red neuronal para cuantificar la relación intensidad – duración de la lluvia, variables que se encuentran interrelacionadas de una forma muy imprecisa. El modelo contiene funciones de transferencia no lineales e incluye términos de naturaleza estadística en la función de error. Para estimar los parámetros de la red neuronal se ha desarrollado un algoritmo de aprendizaje adaptado a funciones de error no derivables.

Descargas

Los datos de descargas todavía no están disponibles.

Citas

Alvarez, J., y S. Bolado (1996). Descripción de los procesos de infiltración mediante redes neuronales artificiales. Ing. Agua. 3: 39 – 46. https://doi.org/10.4995/ia.1996.2697

ASCE task committee on application of artificial neural networks in hydrology (2000). Artificial neural networks in hydrology, I: preliminary concepts. J. Hydrol. Engng. 5: 115 – 123. https://doi.org/10.1061/(ASCE)1084-0699(2000)5:2(115)

Bárdossy, A. (1998). Generating precipitation time series using simulated annealing. Water Resour. Res. 34: 1737 – 1744. https://doi.org/10.1029/98WR00981

Cancelliere, A., G. Giuliano, A. Ancarani y G. Rossi (2002). A neural networks approach for deriving irrigation reservoir operating rules. Water Resour. Mgmt. 16: 71 – 88. https://doi.org/10.1023/A:1015563820136

Cybenko, G. (1989). Approximations by superpositions of a sigmoidal function. Math. Control, Signals Syst. 2: 303 – 314. https://doi.org/10.1007/BF02551274

Dibike, Y. B., D. Solomatine y M. B. Abbott (1999). On the encapsulation of numerical hydraulic models in artificial neural network. J. Hydr. Res. 37: 147 – 161. https://doi.org/10.1080/00221689909498303

Eagleson, P. S. (1978). Climate, soil and vegetation (2): The distribution of annual precipitation derived from storm sequences. Water Resour. Res. 14: 713 – 721. https://doi.org/10.1029/WR014i005p00713

Entakhabi, D., I. Rodríguez Iturbe y P. S. Eagleson (1989). Representation of the temporal rainfall process by a modified Neyman Scott rectangular pulse model: Parameter estimation and validation. Water Resour. Res.25: 295 – 302. https://doi.org/10.1029/WR025i002p00295

Fine, T. L. (1999). Feedforward neural network methodology. Ed. Springer – Verlag. https://doi.org/10.1002/047134608X.W5106

Freeman, J. A., y D. M. Skapura (1993). Redes neuronales: algoritmos, aplicaciones y técnicas de programación. Ed. Addison – Wesley

French, M. N., W. F. Krajewski y R. R. Cuykendall (1992). Rainfall forecasting in space and time using a neural network. J. Hydrol. 137: 1 – 31. https://doi.org/10.1016/0022-1694(92)90046-X

Funahashi, K. I. (1989). On the approximate realization of continuous mappings by neural networks. Neural Networks 2: 183 – 192. https://doi.org/10.1016/0893-6080(89)90003-8

Goel, N. K., R. S. Kurothe, B. S. Mathur y R. M. Vogel (2000). A derived flood frequency distribution for correlated rainfall intensity and duration. J. Hydrol.228: 56 – 67. https://doi.org/10.1016/S0022-1694(00)00145-1

Govindaraju, R. S., y A. Ramachandra Rao (2000). Artificial neural networks in hydrology. Ed. Kluwer Academic Publishers. https://doi.org/10.1007/978-94-015-9341-0

Hagan, M., y M. Menhaj (1994). Training feedforward networks with the Marquardt algorithm. IEEE Trans. On Neural Networks 5: 989 – 993. https://doi.org/10.1109/72.329697

Hecht – Nielsen, R. (1987). Kolmogorov’s mapping neural network existence theorem. Proc. Int. Conf. on Neural Networks 3: 11 – 13, IEEE Press.

Hecht – Nielsen, R. (1990). Neurocomputing. Ed. Addison – Wesley

Hilera González, J. R., y V. J. Martínez Hernando (1995). Redes neuronales artificiales. Fundamentos, modelos y aplicaciones. Ed. Ra – Ma

Himmelblau, D. M. (1972). Applied nonlinear programming. Ed. McGraw – Hill

Hornik, K., M. Stinchcombe y H. White (1990). Universal approximation of an unknown mapping and its derivatives using multilayer feedforward networks. Neural Networks 3: 551 – 560. https://doi.org/10.1016/0893-6080(90)90005-6

Hsu, K. L., H. V. Gupta y S. Sorooshian (1995). Artificial neural network modeling of the rainfall – runoff process. Water Resour. Res. 31: 2517 – 2530. https://doi.org/10.1029/95WR01955

Hsu, K. L., H. V. Gupta, X. Gao y S. Sorooshian (1999). Estimation of physical variables from multichannel remotely sensed imagery using a neural network: application to rainfall estimation. Water Resour. Res. 35: 1605 – 1618. https://doi.org/10.1029/1999WR900032

Hutchinson, M. F. (1990). A point rainfall model based on a three state continuous Markov occurrence process. J. Hydrol. 114: 125 – 148. https://doi.org/10.1016/0022-1694(90)90078-C

Istok, J. D. y L. Boersma (1989). A stochastic cluster model for hourly precipitation data. J. Hydrol. 106: 257 – 285. https://doi.org/10.1016/0022-1694(89)90076-0

Johansson, E. M., F. U. Dowla y D. M. Goodman (1992). Backpropagation learning for multilayer feedforward neural networks using the conjugate gradient method. Int. J. Neural Syst. 2: 291 – 301. https://doi.org/10.1142/S0129065791000261

Kao, J. J. (1996). Neural net for determining DEM based model drainage pattern. J. Irrigation and Drainage Engng. 122: 112 – 121. https://doi.org/10.1061/(ASCE)0733-9437(1996)122:2(112)

Kolmogorov, A. N. (1957). On the representations of continuous functions of many variables by superpositions of continuous functions of one variable and addition. Dokl. Akad. Nauk USSR 114: 953 – 956.

Kurkova, V. (1991). Kolmogorov’s theorem is relevant. Neural Computation 3: 617 – 622. https://doi.org/10.1162/neco.1991.3.4.617

Leshno, M., V. Lin, A. Pinkus y S. Schocken (1993). Multilayer feedforward networks with a nonpolynomial activation function can approximate any function. Neural Networks 6: 861 – 867. https://doi.org/10.1016/S0893-6080(05)80131-5

Maier, H. R., y G. C. Dandy (1999). Empirical comparison of various methods for training feedforward neural networks for salinity forecasting. Water Resour. Res.35: 2591 – 2596. https://doi.org/10.1029/1999WR900150

Martín del Brío, B. y A. Sanz Molina. (1997) Redes neuronales y sistemas borrosos. Ed. Ra – Ma

Mason, J. C., R. K. Price y A. Tem’me (1996). A neural network model of rainfall runoff using radial basis functions. J. Hydr. Res. 34: 537 – 548. https://doi.org/10.1080/00221689609498476

Morshed, J., y J. J. Kaluarachchi (1998). Parameter estimation using artificial neural network and genetic algorithm for free product migration and recovery. Water Resour. Res. 34: 1101 – 1113. https://doi.org/10.1029/98WR00006

Rodríguez Iturbe, I., B. Febres de Powder y J. B. Valdés (1987). Rectangular pulses point processes for rainfall: Analysis of empirical data. J. Geophysical Res. 92: 9645 – 9656. https://doi.org/10.1029/JD092iD08p09645

Rogers, L. L., y F. U. Dowla (1994). Optimization of groundwater remediation using artificial neural networks with parallel solute transport modeling. Water Resour. Res.30: 457 – 481. https://doi.org/10.1029/93WR01494

Schaap, M.G., y W. Bouten (1996). Modeling water retention curves of sandy soils using neural networks. Water Resour. Res. 32: 3033 – 3040. https://doi.org/10.1029/96WR02278

Swingler, K. (1996). Applying neural networks: a practical guide. Ed. Morgan Kaufman Publishers, Inc.

Whitley, R., y T. V. Hromadka II (1999). Approximate confidence intervals for design floods for a single site using a neural network. Water Resour. Res. 35: 203 – 209. https://doi.org/10.1029/1998WR900016