An Evolutionary Model for Earthquake Prediction Considering Time-Series Evolution and Feature Extraction and Its Application

Seismic activity presents characteristics such as relatively concentrated distribution, high destructiveness, huge secondary hazards, complex change patterns, and unpredictable future activity conditions. It is of great theoretical significance and application and promotion value to research magnitu...

Full description

Saved in:
Bibliographic Details
Published in:Journal of physics. Conference series 2022-08, Vol.2333 (1), p.12013
Main Authors: Du, Depeng, Cui, Zhendong
Format: Article
Language:English
Subjects:
Artificial neural networks
Back propagation networks
bidirectional long- and short-term memory networks
convolutional neural networks
Data analysis
Decision analysis
Earthquake prediction
Earthquakes
Feature extraction
Neural networks
Physics
Prediction models
predictive models
Seismic activity
Support vector machines
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Seismic activity presents characteristics such as relatively concentrated distribution, high destructiveness, huge secondary hazards, complex change patterns, and unpredictable future activity conditions. It is of great theoretical significance and application and promotion value to research magnitude prediction for earthquake-prone areas. This study attempts to develop an earthquake prediction model based on seismic data from 1970 to 2021 and to predict earthquakes of magnitude (4.5-6). Firstly, the data are statistically analyzed using data statistics to analyze trends, identify patterns and characteristics of change, and make decisions conducive to development. Secondly, feature extraction and selection are carried out by convolutional neural networks to select the optimal features. The CNN_BiLSTM model was constructed and compared with other prediction models (long and short-term memory neural network, back propagation neural network, and support vector regression) to obtain prediction results for sensitivity, specificity, true prediction values, false prediction values, and accuracy values were compared and analyzed. The earthquake magnitude predictions for Japan and surrounding areas using the above techniques show essential and encouraging results, thus taking an essential step towards an eventual robust prediction mechanism.
ISSN:1742-6588
1742-6596
DOI:10.1088/1742-6596/2333/1/012013