Adaptive neuro-fuzzy inference system based model for rainfall forecasting in Klang River, Malaysia

摘要: Runoff prediction still represents an extremely important issue in applied hydrology. On the other hand, rainfall is one of most complicated effective hydrologic processes runoff prediction. For a developing country such as Malaysia which prone to flood disaster having expert model for forecasting very vital matter. In this article, adaptive neuro-fuzzy inference system (ANFIS) proposed forecast Klang River on monthly basis. To be able to train and test ANFIS ANN models, statistical data from 1997 2008, was obtained gates dam data. The optimum structure input pattern determined through trial error. Different combinations were produced inputs and five different criteria used order evaluate effectiveness each network its ability make precise performance compared artificial neural (ANN) model. five are root mean square error (RMSE), Correlation Coefficient (), Nash Sutcliffe coefficient (NE), gamma (GC) Spearman correlation (SCC). result indicate that showed higher accuracy low Furthermore, estimated by technique closer actual than one.   Key word: Klang gate, ANFIS,