Long Term Forecast of Annual Maximum Peak Discharge at Yangtze Three Gorges Based on Fuzzy Method

A fuzzy model of pattern recognition was established in combining cause-and-effect and statistical analysis with fuzzy analysis, choosing predictors such as rainfall and atmospheric circulation in previous stage which effect the annual maximum peak discharge at Yichang Station of the Yangtze River, giving different weightings to the forecast factors, and making a yearly prediction of annual maximum peak discharge. The results of calculation show that the model is highly effective and the qualified rate of yearly prediction from 1997 to 2004 reaches 100%, the average percentage error is 10%, the simulative error of model is 8.0%.