Monthly Discharge Forecasting in Sefid River Basin Using Fuzzy Neural Network and Artificial Neural Network Models (1987-2012)

River flow predicting is one of the most important factors in surface water recourses management, especially during flood and drought periods. Traditionally, time series analysis and modeling is used for building mathematical models to generate hydrologic data in hydrology and water resources. This research was designed to evaluate the applicability of artificial neural network and adaptive neuro – fuzzy inference system to model monthly discharge in Dehkadeh Sefid station of Sefid River. It must be mentioned, firstly, data were analyzed using SPSS 20 and Wingamma softwares, to select appropriate type and number of training input data and then, they were used in the models. It has been tried to evaluate the applicability of artificial neural networks and neuro - fuzzy techniques to predict monthly discharge. Finally, the accuracy of the results produced by these methods was compared using statistical criterion. Results taken from this research show that artificial neural network in comparison Adaptive Neuro – Fuzzy Inference System has a greater ability on the prediction of monthly discharge in Sefid River.