Forecasting monthly runoff using wavelet neural network model

According to the nonlinear and the multi-time scale character of the Monthly runoff time series, the A Trous Algorithm was used to analyze the Monthly runoff time series of Panshitou Reservoir, Based on this result, the combination forecasting model was built by combining the wavelet analysis and artificial neural network, and the general steps and key algorithm of the model were proposed. This article in view of ordinary BP algorithm existence slow convergence, easy to immerging in partial minimum frequently, proposed one BP algorithm which based on Improved Conjugate Gradient Method. Using this model, simulate and forecast the monthly runoff, The results show that the model of combination wavelet analysis and artificial neural network has better capability of simulation for the process of monthly runoff, and the model used to predict with higher accuracy.