Neural network method for performing short-term earthquake prediction by using earthquake parameters

Abstract

The invention discloses a neural network method for performing short-term earthquake prediction by using earthquake parameters, which is a method for predicting earthquakes by using regression analysis and neural network combined technology and comprises: (1) determining a region to be studied; 2) collecting and preprocessing earthquake catalogues; 3) acquiring the earthquake parameters and time varying parameters by using the earthquake catalogues; 4) sorting information; 5) performing regression analysis; 6) performing neural network simulation; and 7) computing earthquake magnitudes of predicted earthquakes. The method has the advantages that: regional short-term earthquake prediction can be realized and the prediction time is no more than 6 months; earthquake magnitude quantization prediction can be realized, the computing result is stable and the prediction precision is high; the maneuverability and practicality are high; and the regional short-term earthquake prediction result can be used to provide service for 'disaster prevention and reduction', and the social and economic benefits are obvious.

Description

technical field [0001] The invention relates to a method for short-term earthquake prediction using earthquake parameter information and neural network technology, and belongs to the technical field of "disaster prevention and mitigation" in the subject of "earthquake". Background technique [0002] In terms of time, earthquake prediction is divided into long-term prediction (more than 10 years), medium-term prediction (1-10 years), short-term prediction (within 1 year), and short-term prediction (within 1 month, or even within a few days) 4 categories. Strictly speaking, the accuracy of earthquake prediction means that the predicted values ​​of the three elements of time, space and strength (time, space and intensity) must be within the error range. At present, some progress has been made in medium and long-term earthquake prediction, but the level of short-term earthquake prediction is still very low. Earthquake prediction is a scientific problem faced by mankind today, ...

AI Technical Summary

Problems solved by technology

[0005] 1) Most of the current earthquake prediction methods are aimed at a large area and estimate its seismic risk for a long period of time. They do not quantify the earthquake magnitude, but only predict the earthquake trend

[0006] 2) There are some earthquake prediction methods that can quantitatively predict the magnitude of earthquakes, but the prediction accuracy is very low

[0007] 3) There are some earthquake prediction methods based on neural networks, but the calculation time is long, the calculation results are unstable, and the prediction accuracy is low

[0008] 4) At present, most earthquake prediction methods are not very operable and practicable

Images