Research On Flood Forecasting And Disaster Degree Evaluation Base On ANN

This paper is base on the project of "The optimization control technology on the integrated management used in Huaihongxin River", which researches by Anhui Hydraulic Research Institute. The flood forecasting and disaster degree evaluation are studied as the main research contents. Models are building by using ANN and applied to Huaihongxin River, which provides a decision-making basis for flood control.Using back-propagation (BP) ANN and its advanced, a BP neural network model about flood forecasting is established based on of Huaihongxin River of considering the interzone inflow. The predicting results indicate that this model can preferably reflect the influences of interzone inflow to the flood and the precision of this simulation model is acceptable.Then ANN is using in qualitative analysis of flood water logging disaster. Combine with Huaihongxin River, a model is building to classify the disaster degree. The results indicate that ANN can reflect the relationship between indices and disaster grade. So it can be used in disaster classification, and has faster response speed and higher evaluation precision.