Predict typhoon-induced storm surge deviation in a principal component back-propagation neural network model*

题名：Predict typhoon-induced storm surge deviation in a principal component back-propagation neural network model

领域：LIMNOLOGY 四区

来源：CHINESE JOURNAL OF OCEANOLOGY AND LIMNOLOGY

发表年代：2013年
作者：GUO Zhongyang (过仲阳) 1, DAI Xiaoyan (戴晓燕)  , LI Xiaodong (栗小东)  ,YE Shufeng (叶属峰)

To reduce typhoon-caused damages, numerical and empirical methods are often used to forecast typhoon storm surge. However, typhoon surge is a complex nonlinear process that is diffi cult to forecast accurately. We applied a principal component back-propagation neural network (PCBPNN) to predict the deviation in typhoon storm surge, in which data of the typhoon, upstream fl ood, and historical case studies were involved. With principal component analysis, 15 input factors were reduced to fi ve principal components, and the application of the model was improved. Observation data from Huangpu Park in Shanghai, China were used to test the feasibility of the model. The results indicate that the model is capable of predicting a 12-hour warning before a typhoon surge.