Please use this identifier to cite or link to this item:
|Title: ||Forecasting runoff discharge at different lead-time using hybrid HEC-HMS and adaptive network-based fuzzy inference system models|
|Authors: ||WEN-CHENG LIU;CHUAN-EN CHANG;Chih-Chieh Young|
|Issue Date: ||2017-10-24T07:59:09Z
|Publisher: ||Taiwan Water Conservancy|
|Abstract: ||Abstract:Taiwan is located in the hub of the Western Pacific typhoon path, attacked by several typhoons every year. Typhoons brought abundant rainfall make massive runoff in the river, resulting in river overbank flow and a lot of great disasters. Therefore predicting runoff accurately is an important issue of watershed management. In the present study, we selected seven typhoon events occurred in sub-basin of Kaoping River watershed. The combination of the physical rainfall-runoff model and the artificial neural network model was adopted to forecast runoff discharge. The physical model is HEC-HMS model (Hydrological Engineering Center-Hydrological Modelling System) that was developed by the U.S. Army Corps of Engineers for simulating rainfall-runoff processes. Adaptive Network-based Fuzzy Inference System model (ANFIS) was used to combine with HEC-HMS model for forecasting runoff at different lead-time. Li-Ling Bridge in the Kaoping River subwatershed was selected as the outlet of rainfallrunoff for the model calibration (training) and validation. Seven typhoons events were used for model calibration (training) and validation. Six statistical indices is used to evaluate the errors including root mean square error (RMSE), mean absolute error (MAE), correlation coefficient (R), error of time to peak discharge (ETp), error of peak discharge (EQp), and coefficient of efficiency (CE). The results indicate that the HEC-HMS model can not accurately predict runoff discharge. The hybrid of HEC-HMS and ANFIS models can yield a better forecasting in runoff discharge. It also reveals that the capability of forecasting runoff discharge gets worse, when the lead-time increases.|
|Appears in Collections:||[海洋環境資訊系] 期刊論文|
Files in This Item:
There are no files associated with this item.
All items in NTOUR are protected by copyright, with all rights reserved.