Research and Application of Data Mining for Runoff Forecasting

This paper presents a runoff forecasting method based on data mining. A runoff forecasting model is built up by the data mining tool ANN. Data mining is carried on by BP model and the convergence speed is improved by the modification of the weight coefficients. The model is tested in a real project and compared with general models. The test result and analysis illustrate its good precision of forecasting and good value in the application.