simulating rainfall-runoff process with a new combined artificial intelligence

The rainfall-runoff process is one of the most important and complex hydrological phenomena in the management of surface water resources and in taking appropriate measures in the event of floods and droughts. to simulate this process, a proper understanding of the behavior of the basin saves time and plays important role in model selection. to simulate the runoff process of the karkheh catchment in iran, statistical models and artificial intelligence approaches—including multivariate linear regression (mlr), artificial neural network (ann), support vector regression (svr), and support vector regression-wavelet (wsvr)—were applied on a daily time scale over the statistical period from 2010 to 2020. to assess simulation performance, statistical indices such as the coefficient of determination (r²), root mean square error (rmse), mean absolute error (mae), nash-sutcliffe efficiency (nse), and percentage bias (pbias) were utilized. results indicated that the studied models performed better in composite structures, with artificial intelligence models demonstrating lower error rates and superior performance compared to statistical models. notably, the wavelet support vector regression model exhibited greater accuracy and reduced error relative to the other models. overall, the findings suggest that hybrid artificial intelligence models are effective for modeling the runoff process and can serve as a suitable and efficient solution for water resources management.