Using the General Regression Neural Network Method to Calibrate the Parameters of a Sub-Catchment

Computer software is an effective tool for simulating urban rainfall–runoff. In hydrological analyses, the storm water management model (SWMM) widely used throughout world. However, this ineffective parameter calibration and verification owing to complexity associated with monitoring data onsite. present study, general regression neural network (GRNN) predict parameters of catchment directly, which cannot be achieved using SWMM. Then, runoff curve simulated SWMM, employing predicted based on actual rainfall events. Finally, observed curves are compared. The results demonstrate that GRNN helpful achieving simulation high accuracy. Thus, combining SWMM creates rainfall–runoff simulation.