Typhoon surge forecasting with artificial back-propagation neural networks

A typhoon-surge forecasting model was developed with the application of the back-propagation neural network (BPN) in the present paper. This artificial neural network model forecasts the hourly time series of typhoon surge variation based on a set of input data including typhoon's characteristics, local meteorological conditions and typhoon surges at a considered tidal station. For selecting a better forecasting model, four models (Models A, B, C, and D) were tested and compared under the different composition of input factors. A general evaluation index that is a composition of four performance indexes was proposed to evaluate the model's overall performance. Tested results show that Model D composing 18 input factors has best performance among the four models, The Model D was then applied to typhoon-surge forecasting at Cheng-kung Tidal Station in south-eastern coast of Taiwan and at Tung-shih Tidal Station in the coast of south-western Taiwan. Results show that the application of Model D in typhoon-surge forecasting at Cheng-kung Tidal Station has better performance than that at Tung-shih Tidal Station.