Water Level Forecasting in Tidal Rivers during Typhoon Periods through Ensemble Empirical Mode Decomposition

In this study, a novel model that performs ensemble empirical mode decomposition (EEMD) and stepwise regression was developed to forecast the water level of tidal river. Unlike more complex hydrological models, main advantage proposed is only required data are data. EEMD used decompose signals from river into several intrinsic functions (IMFs). These IMFs then reconstruct ocean stream components represent tide flow, respectively. The forecasting obtained through on these components. component at location 1 h ahead can be using observed downstream gauging stations, corresponding stages upstream stations. Summing two forecasted enables in conceptually simple highly accurate. Water collected stations Tanshui River Taiwan during typhoons were assess feasibility model. accurately reliably predicted Taipei Bridge station.