Abbas Parsaie - Ph.D. candidate of Hydro structure engineering, Department of water Engineering, Lorestan University, Khorram Abad, Iran.
Shadi Najafian - M.Sc. Candidate of hydro structures, Department of water Engineering, Lorestan University, Khorram Abad, Iran.
HojattAllah Yonesi - Assistant Professor of Water Engineering, Lorestan University, Khorram Abad, Iran.

Discharge estimation in rivers is the most important parameter in flood management. The compound open channel is the most accurate concept for simulation of river engineering problems. Predicting the flow discharge in the compound open channel by the analytical approach leads to solve a system of complex nonlinear equations. In many complex mathematical problems that lead to solve complex problems, an artificial intelligence models could be used. In this study Adaptive Neuro Fuzzy Inference System (ANFIS) technique was used for modeling and predicting the flow discharge in the compound open channel. Assessing the results of the analytical approaches showed that the divided channel method with horizontal subsection separated lines with correlation coefficient (0.76) and root mean square error (0.162) is accurate among the analytical approaches. The ANFIS model with correlation coefficient (0.98) and root mean square error (0.029) for the testing stage has suitable performance for predicting the discharge of flow in compound open channel. During the development of ANFIS model found that the relative depth ratio, hydraulics radius ratio and ratio of the area are the most influencing parameters in discharge prediction by the ANFIS model.

Soft Computing, Discharge Prediction, Flood Engineering, ANFIS, River Hydraulic