基于神经网络的水文预报方法分析-水利水电工程专业论文.docxVIP

华 华 中 科 技 大 学 硕 士 学 位 论 文 II II ABSTRACT The flood disaster in China happens very frequently, which not only have an impact on the countrys social development, but also threat the peoples life. In order to reduce the loss brought by the flood, lots of measures have been used, such as the flood forecasting model. For the flood control, the accuracy of flood forecasting is one of the most important factors for flood prevention and disaster reduction. Neural network is the most widely used method in hydrological forecast, and the type of forecast factor to establish the neural network input influences the accuracy of the hydrological forecast. In this paper, the copula entropy theory was putted into partial mutual information (PMI) method. The PMI base on the entropy of the Copula was used to the selection of the predictor, which calculates the mutual information value through the copula entropy. In this paper, the BP neural network, the RBF neural network and the GRNN neural network were used to establish the hydrological forecasting model, the copula entropy method and correlation coefficient method were used to select the predictor of the hydrological model, to make the hydrological forecasting for the Yichang hydrological station in Yangtze River basin and the Pingshan hydrological station in the Jinsha River Basin. Test results indicated that in the same neural network of hydrological forecast model, the result based on the entropy of copula are better than the result based on the method of correlation factor, in the same forecast factor conditions, the result based on BP network are better than the forecast result based on RBF network and GRNN network. This paper improved the accuracy of the hydrological forecast through the comparative analysis based on the different forecast factor and the hydrological forecast model for a particular basin, and had very important practical significance on the flood resources and flood prevention and disaster reduction. Keywo