作者: A.B. Dariane , Sh. Azimi
DOI: 10.1080/02626667.2014.988155
关键词:
摘要: ABSTRACTIn this study, a data-driven streamflow forecasting model is developed, in which appropriate inputs are selected using binary genetic algorithm (GA). The process involves combination of GA input selection method and two adaptive neuro-fuzzy inference systems (ANFIS): subtractive (Sub)-ANFIS fuzzy C-means (FCM)-ANFIS. Moreover, the application wavelet transforms coupled with these models tested. Long-term data for Lighvan Ajichai basins Iran used to develop models. results indicate considerable improvements when methods both For example, Nash-Sutcliffe efficiency (NSE) coefficient FCM-ANFIS 0.74. However, applied, NSE improved 0.85. added, performance new hybrid shows noticeable enhancements. value wavelet-FCM-ANFIS 0.97 basin.Editor D. Koutsoyiannis Associate e...