FORECAST FOR MEAN MONTHLY DISCHARGE OF THE CAPLINA RIVER, BY APPLYING ARTIFICIAL NEURAL NETWORK (RNA) AND PERIODIC AUTOREGRESSIVE MODEL PAR (1)
DOI:
https://doi.org/10.26490/uncp.prospectivauniversitaria.2011.8.1261Keywords:
caplina basin, artificial neural networks, series of timeAbstract
Caplina river is the main tributary of the hydrographic basin of the same name, It has an extension of 4 239,09 km2, and because of this reason, it is one of the principal sources of water supply for different uses in Tacna’s city. As a result, diverse entities have been interested in learning about the water current and future availability of the river Caplina, because this is key to plan and manage water resource systems. The stochastic models have been present during a long time, the most common alternative in the prediction of flows. Nowadays, the tools of intelligent computation like the artificial neural networks, specially the networks multi-geld with algorithm of retro-spread. In this context, the current research centers its efforts on the application of the neural networks to the prediction of the average monthly flows of the river Caplinastation Bocatoma Calientes, a model developed from neural networks based on information about flows, rainfall and evaporation, as well as opposite to stochastic models. So, 10 models of artificial neural networks were developed with different architectures, and tried with the first subset of information corresponding to the period 1939 - 1999, and then validated with the second subset of information of the period 2000 - 2006. The models of artificial neural networks showed comparatively better performance as for prediction opposite to a periodic autoregressive model of the first order PAR (1).
Downloads
References
Alegre, A. Simulación de redes neuronales artificiales: Una aplicación didáctica. Tesis Lic. Sistemas. Universidad Nacional del Nordeste. Corrientes, Argentina. 2003.
Dolling, O. Sistemas de apoyo a la gestión integral de cuencas hidrográficas. Tesis Dr. Universidad Nacional San Juan. Santiago, Chile. 2001.
Tokar, A; MARKUS, M. Precipitation-runoof modeling using artificial neural networks and conceptual models. 2000.
Laqui, W. Predicción de caudales mensuales del rio Huancané utilizando modelos de redes neuronales artificiales. 2008.
Dölling, O. Utilización de redes neuronales artificiales al pronóstico de caudales en cuencas nivales. 2001.
Zúñiga, A; Jordán, C. Pronostico de caudales medios mensuales empleando sistemas neurofuzzy. 2005.
Evolución y ordenamiento de los recursos hídricos en las cuencas de los ríos Caplina y Uchusuma, 2002
Downloads
Published
Issue
Section
License
Copyright (c) 2021 Prospectiva Universitaria
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
Esta Revista es de acceso abierto a su contenido a través del Internet, poniendo a disposición de la comunidad científica los resultados de la investigación, de manera gratuita, para el intercambio del conocimiento desarrollado.
El contenidos de la Revista se distribuyen bajo la licencia Creative Commons Reconocimiento-NoComercial-CompartirIgual 4.0 Internacional.