Research of flood prediction based on subjective/objective evidences fusion model

摘要

This paper presents a model by combining BP neural network and DS evidential reasoning, which not only achieves the feature level fusion of all subjective and objective evidences in various domains and layers, but also makes distinct models complement each other. By the experiment, this method improves classification precision by 7.9 percent and reduces the time complexity of algorithm. The model solves the problems such as high complexity of algorithms and low accuracy rate of classifications lie in the flood prediction using single models.