Abstract: In this paper, radial basis function networks based on the wavelet analysis method is introduced to forecast hydrologic time series. Firstly the hydrologic time series is decomposed to different frequency components with wavelet analysis. Then the artificial neural network is used in multi-scale forecasting of these coefficients. Finally, based on the formula reconstructed, the forecasted hydrologic time series is obtained. The effectiveness of this method is verified by an example.

Key words: Yellow River, flow forecasting, radial basis function networks, wavelet analysis