Correo Electrónico
DNINFOA - SIA
Bibliotecas
Convocatorias
Identidad U.N.
Publicado
Estimación de la demanda de agua para riego: Regresiones lineales versus Aproximaciones neuronales
Palabras clave:
Demanda de Agua, Zonas Regables, Redes Neuronales, Regresión Múltiple, Córdoba-España, Riego (es)Water Demand, Irrigation Districts, Neural Networks, Multiple Regression Models (en)
Descargas
La demanda de agua constituye una pieza básica de información para diseñar políticas que afecten al consumo del agua en los regadíos. También es la magnitud de referencia en el diseño, modernización y explotación de los sistemas de distribución. En este trabajo, se propone caracterizar la demanda de agua de riego mediante la aplicación de regresiones lineales y de Redes Neuronales Computacionales (RNCs). Se dispone de datos de consumo diario de agua de la zona regable del Genil-Cabra (Córdoba, España) registrados por un sistema automático de telemetría, durante las campañas de riegos 2001/02 y 2002/03. Los modelos se establecen considerando la relación de los datos presentes y pasados de la demanda, aunque también se analiza la influencia de datos climáticos. La utilización de regresiones múltiples y RNCs ha proporcionado una capacidad aceptable de estimación de la demanda de agua en zonas regables cuando se hace un filtrado previo de las series de datos registradas. Los mejores resultados se obtienen cuando se consideran como variables de entrada o independientes las demandas de los dos días anteriores al de estimación.
Water demand is a basic information for water consumption management in irrigation districts. Forecasting water demand is one of the main problems for designers and managers of water distribution systems. This paper examines methodologies for irrigation demand modelling. Approaches based on linear multiple regressions and computational neural networks (CNNs) are developed. The models are established using actual data recorded from an irrigation water distribution system in southern Spain during two irrigation seasons (2001/02, 2002/03). The input variables used in CNN and multiple regression models are: water demands from previous days; and water demands and climatic data simultaneously. Good results were obtained when original data were modified to reduce the noise by a smoothing process. The best results were obtained when water demand recorded during the two previous days were used as input data.
Referencias
Abrahart, R.J., See, L. y Kneale, P.E., 1999. Using pruning algorithms and genetic algorithms to optimise network architectures and forecasting inputs in a neural network rainfall-runoff model, J. Hydroinformatics, 1(2), pp. 103-114.
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, pp. 2157-2172.
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), pp. 655-670.
Anctil, E, y Rat, A., 2005. Evaluation of neural network streamflow forecasting on 47 watersheds, J. Hydrol. Eng., 10(1), pp. 85-88.
Bloomfield, P., 1976. Fourier analysis of time series: an introduction, John Wiley & Sons, Nueva York.
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, pp. 1033- 1046.
Chiang, Y.-M., Chang, L.-C. y Chang, F.-J., 2004. Comparison of static-feedforward and dynamic- feedback neural networks for rainfall-runoff modeling, J. Hydrol., 290, pp. 297-311.
Coulbeck, B., 1988. Computer control of water supply, Leicester Polytechnic, Leicester.
Cybenco, G, 1989. Approximation by superpositions of a sigmoidal function, Math. Controls, Signals, and Systems, 2: pp. 303-314.
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.
FAO, 1993. Las políticas de recursos hídricos y la agricultura, El estado mundial de la agricultura y la alimentación, Organización de las Naciones Unidas para la Agricultura, Roma.
French, M.N., Krajewski, W.F., y Cuykendall, R.R., 1992. Rainfall forecasting in space and time using a neural network, J. Hydrol., pp. 137,1-31.
Griñó, R., 1992. Neural networks for univariate time series forecasting and their application to water demand prediction, Neural Network World, 2(5): pp. 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, J. Aquacult. Eng., 31, pp. 183-203.
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 (En prensa).
Hsu, K., Gupta, H.V., y Sorooshian, S., 1995. Artificial neural network modeling of the rainfall- runoff process, Water Resour. Res., 31(10): pp. 2517-2530.
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): pp. 1034-1044.
Kuligowski, R.J., y Barros, A.P., 1998. Experiments in short-term precipitation forecasting using artificial neural networks, Mon. Wea. Rev., 126(2), pp. 470-482.
Legates, D.R., y Mccabe JR., GJ., 1999. Evaluating the use of “goodness-of-fit” measures in hydrologic and hydroclimatic model validation, Water Resour. Res., 35(1), pp. 233-241.
Lorrai, M., y Sechi, G.M., 1995. Neural nets for modelling rainfall-runoff transformations, Water Resour. Manage., 9, pp. 299-313.
Martín-Del-Brío, B., y Sanz-Molina, A., 2001. Redes neuronales y sistemas borrosos, Ra-Ma, 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), pp. 537-548.
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, pp. 246-262.
Nash, J.E., y Sutcliffe, J.V., 1970. River flow forecasting through conceptual models. I: A discussion of principles, J. Hydrol., 10, pp. 282-290.
Ohlsson, L., 1995. Hydropolitics-conflicts over water as a development constraint, Zed Books y University Press, Londres.
ONU, 1997. Comprehensive assessment of the freshwater resources of the world, United Nations Department for Policy Coordination and Sustainable Development (DPCSD), Commision on Sustainable Development.
Park, H.-H., 1998. Analysis and prediction of walleye pollock (Theragra chalcogramma) landings in Korea by time series analysis, Fisheries Res., 38, pp. 1-7.
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): pp. 319-331.
Pulido-Calvo, I., Roldán, J., López-Luque, R., y Gutiérrez-Estrada, J.C., 2003. Demand forecasting for irrigation water distribution systems, J. Irrig. and Drain. Eng., 129(6): pp. 422- 431.
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), pp. 457-481.
Rumelhart, D.E., Hinton, G.E., y Williams, R.J., 1986. Learning representations by backpropagation errors, Nature, 323(9): 5pp. 33-536.
Saporta, D., y Muñoz, M., 1994. El consumo en redes de distribución. Predicción diaria de la demanda, Mejora del rendimiento y de la fiabilidad en sistemas de distribución de agua, Cabrera y Vela (eds.), Universidad Politécnica de Valencia, Valencia.
See, L., y Openshaw, S., 2000. Ahybrid multi-model approach to river level forecasting, Hydrol. Sci. J., 45(4), pp. 523-536.
Shepherd, A. J., 1997. Second-Order Methods for Neural Networks, Springer, Nueva York.
Shin, H-S., y Salas, J.D., 2000. Regional drought analysis based on neural networks, J. Hydrol. Eng., 5(2), pp. 145-155.
Sumpsi, J.M., Garrido, A., Blanco, M., Varela, C., y Iglesias, E., 1998. Economía y política de gestión del agua en la agricultura, Ministerio de Agricultura, Pesca y Alimentación y Ed. Mundi- Prensa, Madrid.
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), pp. 21-25.
Thirumalaiah, K., y Deo, M.C., 1998. River stage forecasting using artificial neural networks, J. Hydrol. Eng., 3(1), pp. 26-32.
Thirumalaiah, K., y Deo, M.C., 2000. Hydrological forecasting using neural networks, J. Hydrol. Eng., 5(2), 180-189.
Tokar, A.S., y Johnson, P.A., 1999. Rainfall-runofF modeling using artificial neural networks, J. Hydrol. Eng., 4(3), pp. 232-239.
Tokar, A.S., y Markus, M. 2000. Precipitation-runoff modeling using artificial neural networks and conceptual models, J. Hydrol. Eng., 5(2), pp. 156- 161.
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., Hervás, Y.C., 1995. Artificial neural networks for estimation of kinetic analytical parameters, Anal. Chem., 67(9): pp. 1521-1525.
Ventura, S., Silva, M., Pérez-Bendito, D., Hervás, Y.C., 1997. Computational neural networks in conjunction with principal component analysis for resolving highly nonlinear kinetics, J. Chem. Inf. Comput. Sci., 37(2): pp. 287-291.
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), pp. 285-292.
Zhang, M., Fulcher, J. y Scofield, R.A. 1997. Rainfall estimation using artificial neural network group, Neurocomputing, 16, pp. 97-115.
