ENHANCED LONG-TERM AND SNOW-BASED STREAMFLOW FORECASTING BY ARTIFICIAL INTELLIGENT METHODS USING SATELLITE IMAGERY AND SEASONAL INFORMATION

This paper investigates the simultaneous use of in-situ hydrologic measurements in combination with two different AI methods, namely, Adaptive Neuro Fuzzy Inference System (ANFIS) and Artificial Neural Network (ANN), for developing enhanced long-term streamflow forecasting models. To enhance reliability proposed models’ outputs, a sub-basin method using regionalization approach is proposed. Furthermore, to accelerate training process achieve more accurate handling seasonal changes, parameter representing variations introduced. The models are applied mountainous Talezang basin, southwestern Iran, which there 14-year series monthly data records snow cover area (SCA) obtained from Moderate Resolution Imaging Spectroradiometer (MODIS). results indicate that significantly improves both methods’ performances. Moreover, it deduced information satellite has great impact on model performance accuracy. Comparing flow forecasts showed ANFIS superior ANN.