8.1 Flood simulation by using GAWANN

In flood prediction，much higher runoff time series forecasting accuracy isoften requested.Besides，the forecasting ability，especially the forecasting interval length，is also a significant criterion to be taken into consideration.Inthis study case，the ANN model hybrid wavelet function was applied in thesimulation and prediction process of flood period in Nen River Basin of China.The nodal weight training of ANN model was improved by the hybrid ofparallel genetic algorithm (mentioned in Chapter 3) to reach global optimalbefore carrying out BP at the last iteration.Forecasting ability was then furtherdiscussed by taking three different prediction solutions.

8.1.1 Study area

Nen River basin is one of the largest basins located in the northeast of China.The study area，Taonan sub-basin ......     （共17598字）    [阅读本文]>>