FLOW CATEGORIZATION MODEL FOR IMPROVING FORECASTING

Prediction of high magnitude flows. In this study, the flow range is divided into three regions (low, medium and high flow regions) and the attributes are decided based on the underlying hydrological process of the flow region. A flow forecasting model is applied for each flow region, using only the historical streamflow data as input. The proposed approach is implemented in tryggevaelde catchment (Denmark) for 1- and 3lead days, using the Support Vector Machine, which yields good results, particularly for high flows in a 3-lead days model.