Modeling rainfall-runoff process using soft computing techniques

摘要: Rainfall-runoff process was modeled for a small catchment in Turkey, using 4 years (1987-1991) of measurements independent variables rainfall and runoff values. The models used the study were Artificial Neural Networks (ANNs), Adaptive Neuro-Fuzzy Inference System (ANFIS) Gene Expression Programming (GEP) which are Intelligence (AI) approaches. applied trained tested various combinations variables. goodness fit model evaluated terms coefficient determination (R^2), root mean square error (RMSE), absolute (MAE), efficiency (CE) scatter index (SI). A comparison also made between these traditional Multi Linear Regression (MLR) model. provides evidence that GEP (with RMSE=17.82l/s, MAE=6.61l/s, CE=0.72 R^2=0.978) is capable modeling rainfall-runoff viable alternative to other artificial intelligence MLR time-series methods.