Prediction of Typhoon Losses in the South-East of China Based on B-P Network

Assessing typhoon losses quickly is the foundation to allocate and deliver relief supplies for helping disastrous people pull through difficulties during the process of typhoon and post-disaster immediately. Therefore, a new method for predicting typhoon losses based on back-propagation neural network is presented by using typhoon characters data, historic typhoon loss data, relative geographical spatial data and population data in this paper. Our approaches start with constructing typhoon losses model based on back-propagation neural network. Then, ascertaining input and output variables of training samples is described. In the end, the experiment is done to test the feasibility of methods approached in this paper by using historic land falling typhoon data during 2005-2007 in China south-east. The result indicates that this model is effective and prediction results are good and receptive.