Modeling the climate change impact on a river basins by using global climate change, heuristic methods, and watershed modeling system

Investigation of the hydrological impacts of climate change at the local scale hydropower potential requires the use of a statistical downscaling technique. Global Circulation Models (GCMs) are essential tools used for the future change of climate impact including precipitation and temperature using different scenarios. The GCMs outputs cannot be used directly due to the uncertainty in the spatial resolution between the GCMs and hydrological models. Statistical downscaling techniques involves the development of relationships between the large-scale climatic parameters and the local variables such as temperature and precipitation. In this study, statistical downscaling of monthly areal mean precipitation for Goksun River basin, which is delineated by using Watershed Modeling System (WMS) program, in Turkey was constructed using the Group Method of Data Handling (GMDH), Gene Expression Programming (GEP), and Support Vector Machine (SVM) techniques and compared results to Linear Regression model. The R-value for precipitation SVM model is 0.863, 0.788 for training and testing periods, respectively. The results showed that SVM has the best model performance than the other proposed downscaling models, however, AIC values showed the GEP model has the lowest AIC value. The SVM downscaling result of the GCM scale simulated under both GCM A1B and A2 emission scenarios for areal mean precipitation for study area has been explored and analyzed. The simulated results for both scenarios show a similarity in their average precipitation. Generally, both scenarios anticipate a decrease in the average monthly precipitation during the simulated periods. Therefore, the results of future projections show that the precipitation will decrease during the period of 2021-2100. Keywords: GCM, Statistical downscaling, GEP, GMDH, SVM, Precipitation, WMS