Skip to Main Content
This study employs a back-propagation network as the main structure in flood forecasting to learn and demonstrate the sophisticated nonlinear mapping relationship. A self organizing map network with classification ability is also applied to the solutions and parameters of BPN model in the learning stage, to classify the network parameter rules and obtain the winning parameters. Hence, hydrologic data intervals can then be forecasted, with the outcomes from the previous stage used as the ranges of the parameters in the recall stage. Finally, the effectiveness of methodology is verified by solving a flood discharge forecasting problem in the Wu-Shi basin of Taiwan.