Rural housing typhoon disaster estimation method based on RBF neural network

Abstract

The invention discloses a rural housing typhoon disaster estimation method based on an RBF neural network. The method comprises the following steps: screening typhoon information influencing an evaluated area; calibrating typhoon key parameters, and simulating and determining typhoon wind speed by using a wind field model; according to the insurance underwriting and claim settlement data of the rural housing in the evaluated region, obtaining the insurance loss rate corresponding to each rural housing of the villages and towns under the influence of each typhoon disaster; establishing a prediction model, substituting the obtained typhoon wind speed data and the insurance loss rate data into the prediction model for training, and obtaining an optimal RBF neural network structure; and predicting through the prediction model to obtain the loss rate of each town insurance amount under different typhoon wind speeds, and performing rural housing typhoon disaster assessment of a rural resolution ratio on an assessment region according to a prediction result. The rural housing typhoon disaster pre-evaluation method can realize rural high-resolution rural housing typhoon disaster pre-evaluation by means of the public disaster insurance data and the RBF neural network, is reliable in evaluation result, and is of great significance to disaster prevention and reduction.

Description

technical field [0001] The present invention relates to the technical field of disaster weather forecasting, in particular to a typhoon disaster forecasting method for rural housing based on RBF neural network. Background technique [0002] my country is a country severely affected by typhoons. In recent years, with global warming, the average intensity of typhoons generated in the western Pacific has shown a downward trend, but the average intensity of typhoons landed in my country has gradually increased. Typhoons are one of the products of the interaction between the ocean and the atmosphere, usually accompanied by strong winds, heavy rain and storm surges. It is extremely destructive and often causes secondary disasters such as floods and mudslides. According to statistics, typhoons are the most severe weather disasters affecting coastal cities over the years, and the average number of collapsed houses and deaths is the highest. Compared with cities, rural houses have p...

AI Technical Summary

Problems solved by technology

[0007] Aiming at the above-mentioned problems in the existing technology, it aims to provide a typhoon disaster prediction method for rural housing based on RBF neural network, effectively establish a typhoon disaster assessment model from disaster-causing factors to disaster-affected body losses, and solve the traditional risk assessment space. For the problems of low resolution and difficult risk measurement, accurate risk and disaster prediction of townships and villages, quantitative assessment of typhoon disaster risk, and scientific basis for subsequent formulation of typhoon disaster insurance policies, typhoon emergency plans and other applications

Images