Research on Runoff Predicting Based on Wavelet Neural Network Conjunction Model

Abstract

A new hybrid model that combines wavelet analysis (WA) and artificial neural network (ANN) called the wavelet neural network (WNN) model is proposed and applied for runoff time series prediction. In this paper, BP network is selected as the neural network, the Morlet wavelet is chosen as the hidden excitation function of precipitation model, the MATLAB is used to write WNN prediction program and the model is trained and tested by the year runoff time series of Tangnaihai Station located in Yellow River upper stream from 1956 to 2008. The hybrid model (WNN) was compared with the back propagation artificial neural network (BPANN) model. The performance of forecasting accuracy of the WNN model is relatively high comparing the traditional approach. The hybrid model (WNN) is a reliable and practical method for runoff prediction.