REGIONAL ANALYSIS OF DAILY PRECIPITATION STOCHASTIC MODEL PARAMETERS USING ARTIFICIAL NEURAL NETWORKS

摘要

The development and the implementation of successful water resources management toolsto assess engineering and environmental problems, such as flood control, on-line reservoiroperation, hydropower generation, water quality control or river ecosystem constraints,among several others, often require the analysis, simulation and prediction of rainfall data.The Markov Chain-Mixed Exponential stochastic model (MCME) is extensively used forestimation of rainfall data. In spite of this method's wide acceptability, improvements inorder to estimate the Fourier coefficients of the MCME model at ungaged meteorologicalstations are incorporated in this paper. The performance of feed forward neural networks(CNNs) to forecast the coefficients of the MCME model at basins in southern Spain areanalyzed. Historical precipitation data from 15 meteorological stations in Andalucía(Spain), each with 52-year daily precipitation records (1953-2004), are used to test theefficiency of incorporated improvements. For that purpose several CNN models, trainedwith the Levenberg-Marquardt algorithm, are implemented and compared.The performance of the MCME model through the weighting interpolation model wascompared with neural approaches as data-driven to generate daily precipitation records inlocations where observed rainfall records are not available. To assess the performance ofthe models during the validation phase and therefore to identify the best model, severalmeasures of accuracy are applied, as there is not a unique and more suitable performanceevaluation test.