A Study on a New Method for the Analysis of Flood Risk Assessment Based on Artificial Neural Network

Abstract

This paper presents a composite method for flood disaster risk assessment using a BP artificial neural network. In order to test the grade criterions of flood disaster loss and resolve the non-uniformity problem of evaluation results of disaster loss indexes, and to raise the grade resolution of flood disaster loss, a BP artificial neural network is suggested for evaluating the grade model of flood disaster, where the disaster loss grade is continuous real number. Meanwhile, an artificial neural network model-BP neural network is used to map multi-dimensional space of disaster situation to one-dimensional disaster situation nonlinearly and to raise the grade resolution of flood disaster loss. Furthermore, its application is verified in the flood risk analysis in Henan Province, China, and the risks of different flood grades are obtained. The results indicate that the methods are effective and practical and therefore the model is considered to have a good application prospect in disaster risk assessment.