M. Zakermoshfegh - PhD Student of Civil Engineering, Tarbiat Modarres University
M. Ghodsian - Associate Professor of Hydraulic Engineering, Tarbiat Modarres University
Gh.A. Montazer - Assistant Professor of Electrical Engineering, Tarbiat Modarres University

River flowforecasting is required to provide important information on a wide range of cases related to design and operation of river systems. Since there are a lot of parameters with uncertainties and non-linear relationships, the calibration of conceptual or physically-based models is often a difficult and time consuming procedure. So it is preferred to implement a heuristic black box model to perform a non-linear mapping between the input and output spaces without detailed consideration of the internal structure of the physical process.The base of intelligent methods is to use the inner knowledge of data, extraction of native relationships between them and generalization in other locations.Artificial Neural Network (ANN) is one of the most popular methods of artificial intelligence that mimics the characteristics of the human brain and saves the information of data in the network weights during the training process. In this study, the capability of ANNs for stream flow forecasting in the Sulaghan river at Kan hydrometric station was investigated. Two types of ANNs namely Multi Layer Perceptron (MLP) and Radial Basis Function (RBF) network were introduced and implemented. The results show that the discharge can be adequately forecasted by these kinds of ANNs.