PEAK-FLOW FORECASTING WITH GENETIC ALGORITHM AND SWMM

The success of a catchment model is known to depend a great deal on th e catchment-model calibration scheme applied to it. This paper present s the application of a genetic algorithm (GA) in the search for the op timal values of catchment calibration parameters. GA is linked to a wi dely used catchment model, the storm water management model (SWMM), an d applied to a catchment in Singapore of about 6.11 km(2) in size. Six storms were considered: three for calibration and three for verificat ion. The study shows that GA requires only a small number of catchment -model simulations and yet yields relatively high peak-flow prediction accuracy. The prediction error ranges from 0.045% to 7.265%.