Modeling Monthly Rainfall in Southern Baluchestan Basin

Flood and drought have caused several damages in natural and unnatural ecosystems in recent decade. Rainfall prediction can be useful in water resource management. The goal of this study is modeling the monthly precipitation of south east of Iran in South-Baluchistan basin, using artificial neural network (ANN) and stochastic models. This area has an unpredictable and complicated monthly rainfall pattern due to impact of several different precipitation systems of other surrounding regions. SARIMA time series models and Time Delay Neural Network (TDNN) are used in monthly precipitation forecasting. Monthly time series of rainfall during 1351-52 to 1387-88 in selected station were used in this study. Stations selection was based on Geographical distribution and data quality. Comparing the results of models of forecasting showed that TDNN model is superior to SARIMA time series model due to different rainfall systems and very sporadic precipitation in this area.