LONG-TERM PROJECTION OF STORM SURGE CHANGE BY NEURAL NETWORK BASED ON STOCHASTIC TROPICAL CYCLONE MODEL

Abstract

 A long-term assessment of storm surge using the stochastic typhoon model (STM) is one of the secured methodology with the large number of samples of the reproducibility is desired if we can estimate storm surge from STM. This study has improved statistical maximum storm surge model, which uses only typhoon information, in the three major bays using artificial neural network (NN). In order to estimate long-term changes in storm surge characteristics under future climate conditions, NN uses STM and climate database for Policy Decision making for Future climate change (d4PDF). The long-term impact assessments of storm surge using several scenarios are compared.