Prediction of annual runoff using adaptive network based fuzzy inference system

Annual runoff forecasting is very important for improvement of the management performance of water resources: high accuracy in runoff prediction can lead to more effective use of water resources. The purpose of this study is to apply the adaptive network based fuzzy inference system (ANFIS) model to forecast annual runoff of Yamadu hydrological station in Xinjiang Province, China. The subtractive clustering algorithm is used to identify the structure of the ANFIS and a hybrid learning algorithm is used for system training. Based on the relative percentage errors, we can see that the ANFIS model has better forecasting performance than artificial neural network (ANN) model.