Rainfall Runoff Modeling using Group Method of Data Handling (GMDH) and Artificial Neural Network (ANN) IN In Polrood Basin

Rainfall-runoff modeling is an essential process and very complicated phenomena that is necessary for proper reservoir system operation and successful water resources planning and management. There are different methods like conceptual and numerical methods for modeling of this process. Theoretically, a system modeling required explicit mathematical relationships between inputs and outputs variables. Developing such explicit model is very difficult because of unknown relationship between variables and substantial uncertainty of variables. In this case, Data driven methods which are based on imprecise conditions and evolutionary algorithms have shown capabilities in many nonlinear systems identification and control issues. One of these intelligent methods is Group Method of Data Handling (GMDH). This method produce complex model during the performance evaluation of input and output information sets increasingly. So in this research we have developed a model based on GMDH for rainfall-runoff modeling in Polrood basin located in North of Iran in Guilan province. Results have evaluated using statistical criteria and compared with an artificial neural network (ANN) model. Results have shown the high performance of two methods for rainfall runoff modeling in dairy scales. Based on statistical criteria, experiment results indicates that the GMDH model was powerful tool to model rainfall runoff time series and can be applied successfully in complex hydrological modeling.