Study on wavelet network model and its application to the prediction of daily discharge

Based on the multi-time scale and the nonlinear character of the daily discharge time series,the wavelet network model a hybrid model between wavelet and artificial neural network(ANN),is presented.The suggested model has super advantage with its absorbing some merits of wavelet and artificial neural network.The predicted accuracy has been risen and the length of predicted time has been lengthened.The prediction of daily discharge at Cuntan station of the Yangtze River in China is researched.The results show that the presented model is satisfactory.