Regional Short-Term Earthquake Prediction Model Based on BP Neural Network

Abstract

A method which gives the quantitative prediction for earthquake magnitude is proposed in this paper. By this method, after calculating the earthquake parameters and the astronomical time-varying parameters, an earthquake prediction model can be established to gives the quantitative prediction for earthquake magnitude in the future prediction period. In this research, the research object was the experimental areas, the prediction period was 6 months, and Linear Regression analysis and conventional BP (Back Propagation) Neural Network were used respectively in prediction. Through backtracking test, the RMSEs(root mean square error) of earthquake magnitude prediction are ±0.78 ML and ±0.61 ML. Then after summarizing the advantages and disadvantages of the two methods, an integrated model based on linear regression and neural network was proposed. Through backtracking test, the RMSE of earthquake magnitude prediction reaches ± 0.41 ML, results improving significantly.