Aproximaciones neuronales univariantes para la predicción de caudales diarios en cuencas portuguesas

  1. Pulido Calvo, Inmaculada
  2. Portela, Maria Manuela
Revista:
Ingeniería del agua

ISSN: 1134-2196

Año de publicación: 2007

Volumen: 14

Número: 2

Páginas: 97-112

Tipo: Artículo

DOI: 10.4995/IA.2007.2905 DIALNET GOOGLE SCHOLAR lock_openAcceso abierto editor

Otras publicaciones en: Ingeniería del agua

Objetivos de desarrollo sostenible

Resumen

Desde hace unos años, las redes neuronales computacionales están siendo una de las herramientas más prometedoras para la estimación de caudales en cuencas. La mayoría de los trabajos de la literatura utilizan para las predicciones, junto con los datos registrados de caudales, otras variables de entrada de carácter hidro-meteorológico. En este estudio se analizó el funcionamiento de redes neuronales de retropropagación para la estimación de caudales diarios en cuencas portuguesas, considerando que sólo los datos de caudal de días previos están disponibles para la calibración de los modelos. Además de los modelos tradicionales de redes neuronales que tienen como variables de entrada los caudales en días previos, se realizó un procedimiento de convolución en las neuronas de la capa de entrada y se probó una metodología híbrida combinando redes neuronales computacionales y modelos ARIMA. Los modelos neuronales complementados con un proceso de convolución dieron las mejores estimaciones considerando los caudales de los tres días previos como variables de entrada. También se realizó un análisis preliminar de la capacidad de esta aproximación para estimar caudales diarios en una cuenca diferente a la utilizada para la calibración de los modelos, obteniéndose resultados satisfactorios.

Referencias bibliográficas

  • Abrahart, R.J., See, L. y Kneale, P.E., (1999). Using pruning algorithms and genetic algorithms to optimize network architectures and forecasting inputs in a neural network rainfall-runoÆ model. J. Hydroinformatics, 1(2), 103-114. https://doi.org/10.2166/hydro.1999.0009
  • Abrahart, R.J. y See, L., (2000). Comparing neural network and autoregressive moving average techniques for the provision of continuous river flow forecasts in two contrasting catchments. Hydrol. Process., 14, 2157-2172. https://doi.org/10.1002/1099-1085(20000815/30)14:11/12<2157::AID-HYP57>3.0.CO;2-S
  • Abrahart, R.J. y See, L., (2002). Multi-model data fusion for river flow forecasting: an evaluation of six alternative methods based on two contrasting catchments. Hydrol. Earth Syst. Sci., 6(4), 655-670. https://doi.org/10.5194/hess-6-655-2002
  • Al-Saba, T. y El-Amin, I., (1999). Artificial neural networks as applied to long-term demand forecasting. Artif. Intell. Eng., 13(2), 189-197. https://doi.org/10.1016/S0954-1810(98)00018-1
  • Alvarez, J. y Bolado, S., (1996). Descripción de los procesos de infiltración mediante redes neuronales artificiales. Ing. Agua, 3(2), 39-46. https://doi.org/10.4995/ia.1996.2697
  • American Society of Civil Engineering (ASCE) Task Committee on Application of Artificial Neural Networks in Hydrology, (2000a). Artificial neural networks in hydrology. I: Preliminary concepts. J. Hydrol. Eng., 5(2), 115-123. https://doi.org/10.1061/(ASCE)1084-0699(2000)5:2(115)
  • American Society of Civil Engineering (ASCE) Task Committee on Application of Artificial Neural Networks in Hydrology, (2000b). Artificial neural networks in hydrology. II: Hydrologic applications. J. Hydrol. Eng., 5(2), 124-137. https://doi.org/10.1061/(ASCE)1084-0699(2000)5:2(124)
  • Anctil, F. y Rat, A., (2005). Evaluation of neural network streamflow forecasting on 47 watersheds. J. Hydrol. Eng., 10(1), 85-88. https://doi.org/10.1061/(ASCE)1084-0699(2005)10:1(85)
  • Box, G.E.P. y Jenkins, G.M., (1976). Time series analysis: Forecasting and control, Holden-Day, Oakland, California.
  • Cameron, D., Kneale, P. y See, L., (2002). An evaluation of a traditional and a neural net modelling approach to flood forecasting for an upland catchment. Hydrol. Process., 16, 1033-1046. https://doi.org/10.1002/hyp.317
  • Chang, F.-J. y Chen, Y.-C., (2001). A counter propagation fuzzy-neural network modeling approach to real time streamflow prediction. J. Hydrol., 245, 153-164. https://doi.org/10.1016/S0022-1694(01)00350-X
  • Chiang, Y.-M., Chang, L.-C. y Chang, F.-J., (2004). Comparison of static-feedforward and dynamic-feedbackward neural networks for rainfall-runoff modeling. J. Hydrol., 290, 297-311. https://doi.org/10.1016/j.jhydrol.2003.12.033
  • De Vries, B. y Principe, J.C., (1991). A theory for neural networks with time delays, Advances in neural information processing systems 3, Morgan Kaufmann Publishers, California.
  • Duan, Q., Sorooshian, S. y Gupta, V.K., (1992). Effective and efficient global optimization for conceptual rainfall-runoff models. Water Resour. Res., 28(4), 1015-1031. https://doi.org/10.1029/91WR02985
  • Duan, Q., Gupta, V.K. y Sorooshian, S., (1993). A shuffled complex evolution approach for effective and effcient global minimization. J. Optim. Theory Appl., 73(3), 501-521. https://doi.org/10.1007/BF00939380
  • Duan, Q., Sorooshian, S. y Gupta, V.K., (1994). Optimal use of SCE-UA global optimization method for calibrating watershed models. J. Hydrol., 158, 265-284. https://doi.org/10.1016/0022-1694(94)90057-4
  • French, M.N., Krajewski, W.F. y Cuykendall, R.R., (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
  • Griñó, R., (1992). Neural networks for univariate time series forecasting and their application to water demand prediction. Neural Network World, 2(5), 437-450.
  • Gutiérrez-Estrada, J.C., de Pedro-Sanz, E., López-Luque, R. y Pulido-Calvo, I., (2004). Comparison between traditional methods and artificial neural networks for ammonia concentration forescasting in an eel (Anguilla anguilla L.) intensive rearing system. Aquacult. Eng., 31, 183-203. https://doi.org/10.1016/j.aquaeng.2004.03.001
  • Gutiérrez-Estrada, J.C., de Pedro-Sanz, E., López-Luque, R. y Pulido-Calvo, I., (2005). Estimación a corto plazo de la temperatura del agua. Aplicación en sistemas de producción en medio acuático. Ing. Agua, 12(1), 77-92. https://doi.org/10.4995/ia.2005.2553
  • Hansen, J.V. y Nelson, R.D., (1997). Neural networks and traditional time series methods: a synergistic combination in state economic forecasts. IEEE Tran. Neural Networks, 8(4), 863-873. https://doi.org/10.1109/72.595884
  • Hsu, K., Gupta, H.V. y Sorooshian, S., (1995). Artificial neural network modeling of the rainfall-runoff process. Water Resour. Res., 31(10), 2517-2530. https://doi.org/10.1029/95WR01955
  • Jakeman, A.J. y Hornberger, G.M., (1993). How much complexity is warranted in a rainfall-runoff model? Water Resour. Res., 29(8), 2637-2649. https://doi.org/10.1029/93WR00877
  • Kitanidis, P.K. y Bras, R.L., (1980). Real time forecasting with a conceptual hydrological model. 2: Applications and results. Water Resour. Res., 16(6), 1034-1044. https://doi.org/10.1029/WR016i006p01034
  • Kuligowski, R.J. y Barros, A.P., (1998). Experiments in short-term precipitation forecasting using artificial neural networks. Mon. Wea. Rev., 126(2), 470-482. https://doi.org/10.1175/1520-0493(1998)126<0470:EISTPF>2.0.CO;2
  • Legates, D.R. y McCabe Jr, G.J., (1999). Evaluating the use of “goodness-of-fit" measures in hydrologic and hydroclimatic model validation. Water Resour. Res., 35(1), 233-241. https://doi.org/10.1029/1998WR900018
  • Lorrai, M. y Sechi, G.M., (1995). Neural nets for modelling rainfall-runoff transformations. Water Resour. Manage., 9, 299-313. https://doi.org/10.1007/BF00872489
  • Martín-del-Brío, B. y Sanz-Molina, A., (2001). Redes neuronales y sistemas borrosos, RaMa, Madrid.
  • Mason, J.C., Tem'me, A. y Price, R.K., (1996). A neural network model of rainfall-runoff using radial basis functions. J. Recherches Hydrauliques, 34(4), 537-548. https://doi.org/10.1080/00221689609498476
  • Moradkhani, H., Hsu, K., Gupta, H.V. y Sorooshian, S., (2004). Improved streamflow forecasting using self-organizing radial basis function artificial neural networks. J. Hydrol., 295, 246-262. https://doi.org/10.1016/j.jhydrol.2004.03.027
  • Nash, J.E. y Sutcliffe, J.V., (1970). River flow forecasting through conceptual models. I: A discussion of principles. J. Hydrol., 10, 282-290. https://doi.org/10.1016/0022-1694(70)90255-6
  • Palazón, J. y García, A., (2004). Modelado de series climatológicas mediante una red neuronal artificial. Ing. Agua, 11(1), 41-52. https://doi.org/10.4995/ia.2004.2521
  • Park, H.-H., (1998). Analysis and prediction of walleye pollock (Theragra chalcogramma) landings in Korea by time series analysis. Fisheries Res., 38, 1-7. https://doi.org/10.1016/S0165-7836(98)00118-0
  • Pérez-Marín, D., Garrido-Varo, A., Guerrero, J.E. y Gutiérrez-Estrada, J.C., (2006). Use of artificial neural networks in near-infrared reflectance spectroscopy calibrations for predicting the inclusion percentages of wheat and sunflower meal in compound feedingstuffs. Appl. Spect., 60(9), 1062-1069. https://doi.org/10.1366/000370206778397506
  • Portela, M.M. y Quintela, A.C., (2000). A altura do escoamento anual médio numa bacia hidrográfica como parâmetro de regionalizaçao de informaçao hidrométrica (Mean annual flow height as a regionalization parameter of hydrologic information), 1 Congresso sobre Aproveitamentos e Gestao de Recursos Hídricos em Países de Idioma Português, Rio de Janeiro, Brasil, 218-227.
  • Portela, M.M. y Quintela, A.C., (2002a). Assessment of the streamflow characteristics under unavailability of discharge data: the mean annual flow depth over the watershed as a regionalization parameter. The Portuguese case, 2002, EGS Conference, Nice, Francia.
  • Portela, M.M. y Quintela, A.C., (2002b). Evaluation of the water resources in Portuguese watersheds without streamflow data. International Conference of Basin Organizations, Madrid, España.
  • Portela, M.M. y Quintela, A.C., (2005). Regionalization of hydrologic information: establishment of flow series at ungauged watersheds, Water Resources Management 2005, Third International Conference on Water Resources Management, Wessex Institute of Technology, UK, and University of Coimbra, Portugal.
  • Pulido-Calvo, I., Roldán, J., López-Luque, R. y Gutiérrez-Estrada, J.C., (2002). Técnicas de predicción a corto plazo de la demanda de agua. Aplicación al uso agrícola. Ing. Agua, 9(3), 319-331. https://doi.org/10.4995/ia.2002.2622
  • Pulido-Calvo, I., Roldán, J., López-Luque, R. y Gutiérrez-Estrada, J.C. (2003) Demand forecasting for irrigation water distribution system. J. Irrig. Drain. Eng., 129(6), 422-431. https://doi.org/10.1061/(ASCE)0733-9437(2003)129:6(422)
  • Pulido-Calvo, I., Montesinos, P., Roldán, J. y Ruiz-Navarro, F.J., (2005). Estimación de la demanda de agua para riego: Regresiones lineales versus aproximaciones neuronales. Avances en Recursos Hidráulicos, 12, 7-19.
  • Qi, M. y Zhang, G.P., (2001). An investigation of model selection criteria for neural network time series forecasting. Eur. J. of Oper. Res., 132, 666-680. https://doi.org/10.1016/S0377-2217(00)00171-5
  • Roger, L.L. y Dowla, F.U., (1994). Optimization of groundwater remediation using artificial neural networks with parallel solute transport modeling. Water Resour. Res., 30(2), 457-481. https://doi.org/10.1029/93WR01494
  • Rumelhart, D.E., Hinton, G.E. y Williams, R.J., (1986). “Learningrepresentations by back-propagation errors. Nature, 323, 533-536. https://doi.org/10.1038/323533a0
  • See, L. y Openshaw, S., (2000). A hybrid multimodel approach to river level forecasting. Hydrol. Sci. J., 45(4), 523-536. https://doi.org/10.1080/02626660009492354
  • Shepherd, A.J., (1997). Second-Order Methods for Neural Networks, Springer, Nueva York. https://doi.org/10.1007/978-1-4471-0953-2
  • Shin, H-S. y Salas, J.D., (2000). Regional drought analysis based on neural networks. J. Hydrol. Eng., 5(2), 145-155. https://doi.org/10.1061/(ASCE)1084-0699(2000)5:2(145)
  • Sorooshian, S., Duan, Q. y Gupta, V.K., (1993). Calibration of rainfall-runoff models: Application of global optimization to the Sacramento soil moisture accounting model. Water Resour. Res., 29(4), 1185-1194. https://doi.org/10.1029/92WR02617
  • Tan, Y. y van Cauwenberghe, A., (1999). Neural-network-based d-step-ahead predictors for nonlinear systems with time delay. Eng. Applic. Artif. Intell., 12(1), 21-25. https://doi.org/10.1016/S0952-1976(98)00043-8
  • Thirumalaiah, K. y Deo, M.C., (1998). River stage forecasting using artificial neural networks. J. Hydrol. Eng., 3(1), 26-32. https://doi.org/10.1061/(ASCE)1084-0699(1998)3:1(26)
  • Thirumalaiah, K. y Deo, M.C., (2000). Hydrological forecasting using neural networks. J. Hydrol. Eng., 5(2), 180-189. https://doi.org/10.1061/(ASCE)1084-0699(2000)5:2(180)
  • Tokar, A.S. y Johnson, P.A., (1999). Rainfall-runoff modeling using artificial neural networks. J. Hydrol. Eng., 4(3), 232-239. https://doi.org/10.1061/(ASCE)1084-0699(1999)4:3(232)
  • Tokar, A.S. y Markus, M., (2000). Precipitation-runoff modeling using artificial neural networks and conceptual models. J. Hydrol. Eng., 5(2), 156-161. https://doi.org/10.1061/(ASCE)1084-0699(2000)5:2(156)
  • Tsoukalas, L.H. y Uhrig, R.E., (1997). Fuzzy and neural approaches in engineering, Wiley Interscience, Nueva York.
  • Ventura, S., Silva, M., Pérez-Bendito, D. y Hervás, C., (1995). Artificial neural networks for estimation of kinetic analytical parameters. Anal. Chem., 67(9), 1521-1525. https://doi.org/10.1021/ac00105a007
  • Wedding II, D.K. y Cios, K.J., (1996). Time series forecasting by combining RBF networks, certainty factors, and the Box-Jenkins model. Neurocomputing, 10, 149-168. https://doi.org/10.1016/0925-2312(95)00021-6
  • Wilson, J.H. y Keating, B., (1996). Business forecasting, Irwin, Londres.
  • Yang, C.C., Prasher, S.O., Lacroix, R., Sreekanth, S., Patni, N.K. y Masse, L., (1997). Artificial neural network model for subsurface-drained farmland. J. Irrig. Drain. Eng., 123(4), 285-292. https://doi.org/10.1061/(ASCE)0733-9437(1997)123:4(285)
  • Yapo, P.O., Gupta, H.V. y Sorooshian, S., (1996). Automatic calibration of conceptual rainfall-runoÆ models: sensitivity to calibration data. J. Hydrol., 181, 23-48. https://doi.org/10.1016/0022-1694(95)02918-4
  • Zhang, G.P., (2003). Time series forecasting using a hybrid ARIMA and neural network model. Neurocomputing, 50, 159-175. https://doi.org/10.1016/S0925-2312(01)00702-0
  • Zhang, M., Fulcher, J. y Scofield, R.A., (1997). Rainfall estimation using artificial neural network group. Neurocomputing, 16, 97-115. https://doi.org/10.1016/S0925-2312(96)00022-7
  • Zhang, G.P., Patuwo, B.E. y Hu, M.Y., (2001). A simulation study of artificial neural networks for nonlinear time-series forecasting. Comp. Oper. Res., 28(4), 381-396. https://doi.org/10.1016/S0305-0548(99)00123-9
Fuente de los datos: Dialnet