Simulation of Rainfall-Runoff Process using Artificial Neural Network and Adaptive Neuro-Fuzzy Interface System(Case Study: Hajighoshan Watershed)

Short-term runoff forecasting is very important due to direct relationship between mangers approach with loss of life by flood. In this study، daily rainfall-runoff modeling was carried out in Hajighoshan watershed using artificial neural networks (ANNs) and adaptive neuro-fuzzy interface system (ANFIS) with different inputs (current day rainfall; current rainfall and pervious day rainfall; current rainfall، pervious day rainfall and two previous day) methods. Also، the different functions i. e. Gaussian، Gaussian 2، Triangular، Gaussian Bell shape were used to ANFIS and number of neurons at hidden layer of ANNs were changed between 2 to 10 neurons. Root mean squared error (RMSE)، mean absolute error (MAE) and correlation coefficient (R) statistics are employed to evaluate the performance of the ANNs and ANFIS models for runoff forecasting. Based on the results of test stage، ANFIS with RMSE=7. 11، MAE=2. 18 and R=0. 60 is superior to rainfall-runoff modeling than the ANN with RMSE=6. 03، MAE=1. 97 and R=0. 39.