| description abstract | This study develops an original methodology for forecasting real-time reservoir inflow hydrographs during typhoons, taking advantage of meteoro-hydrological methods such as analysis of typhoon hydrographs, numerical typhoon track forecasts, statistic typhoon central impulse-based quantitative precipitation forecasts model based on a real-time revised approach (TCI-RTQPF), real-time recurrent learning neural network (RTRLNN), and adaptive network-based fuzzy inference system (ANFIS). To derive the inflow hydrograph induced by interaction between typhoon rain bands, terrain, and monsoons, the inventive novel ensemble numerical-statistic impulse techniques are employed. The inflow during peak flow, inflection, and direct runoff ending (DRE) periods (impulse signal) are used for the deriving process. The hydrograph analysis is used to examine the mechanism between typhoon center location, wind field, precipitation, and the inflow hydrograph, and to establish the evaluation methods. Additionally, a novel total inflow forecast model is developed using image hashing and ANFIS for selecting optimal derived hydrograph. The experiment is conducted in the Tseng-Wen Reservoir basin, Taiwan. Results demonstrate that the wind field–based and moving dynamics–based approach of typhoon can effectively evaluate the time of peak flow, inflection point, and DRE incorporating terrain and monsoon effects. The effective functions for deriving impulse signal include blended polynomial, exponential, and power functions, and for deriving inflow hydrograph, multinomial Gaussian functions. Finally, the real-time experimental outcomes show that the proposed innovative practical methodology can accurately forecast the real-time reservoir inflow hydrograph that the average error of Typhoon Krosa is 7.81% within 32 h average forecasted lead time, and Typhoon Morakot, 9.78% within 79 h forecasted lead time. | |
