Wavelet-neural network model based complex hydrological time series prediction

Time series prediction is one of the main research topics in time series analysis,which is of great importance both in theoretical and application aspects.To improve the performance of the wavelet-neural network model on a complex time series,a novel multi-factor prediction model was proposed.According to the adaptability of different wavelet functions to hydrological time series,a new criterion for the selection of different wavelet functions was also put forward,which was based on weighted correlation coefficients.Finally,the newly proposed method was tested on predicting the daily flow of Wangjiaba Station,which is a very important observation site on Huaihe River.It was found that the chosen Haar wavelet and B3 spline wavelet can produce higher prediction accuracy,which validates the effectiveness of the selecting principle of wavelet function.Compared with the traditional wavelet neural network for single time series,at least 10% improvement was observed for different predicting periods,and 15% improvement in forecasting the high flow direction during the disastrous flood period.All the experimental results showed that the proposed multi-factor prediction model is effective for complex hydrological time series prediction.