A Method of Flood Forecasting of Chaotic Radial Basis Function Neural Network
Jiancang Xie, Tianping Wang, Jianlong Zhang, Yu Shen · 2010
To establish a better flow of the flood forecasting model. Based on chaos theory and RBF neural network forecasting model, and measured flood sequence of space reconstruction by training samples using MATLAB7.0 toolbox sure that the network structure. The RBF forecast model was used Fen he Shi tan Hydrometric Station in 2004 measured the largest flood forecasts, and The results showed the pass rate, with an average relative error, correlation coefficient (R), root mean square error (RMSE) and Nash -Sutcliffe coefficient (NSC) were 100%, 4.69%, 0.979 3,4.226 0 and 0.955 2, and the traditional Volterra adaptive prediction model were 93.75%, 8.97%, 0.954 0,10.263 2 and 0.735 8, RBF model can be seen better results and has been made large flow flood peak better numerical prediction. Chaos theory and the RBF neural network build predictive models to improve flood forecasting accuracy as a new attempt.