A combining earthquake forecasting model between deep learning and Epidemic-Type Aftershock Sequence (ETAS) model

TL;DR

This paper introduces CL-ETAS, a hybrid earthquake forecasting model combining ConvLSTM and ETAS, which improves prediction accuracy, stability, and interpretability over traditional methods using real seismic data.

Contribution

The paper presents a novel composite model that integrates deep learning with empirical seismic laws, enhancing earthquake forecasting performance.

Findings

CL-ETAS outperforms ETAS and ConvLSTM in forecasting accuracy.

The model improves stability and interpretability of earthquake forecasts.

Experimental results based on Southern California data validate the model's effectiveness.

Abstract

The scientific process of earthquake forecasting involves estimating the probability and intensity of earthquakes in a specific area within a certain timeframe, based on seismic activity laws and observational data. Epidemic-Type Aftershock Sequence (ETAS) models, which rely on seismic empirical laws, is one of the most commonly used methods for earthquake forecasting. However, it underestimates feature in short-term time scale and overestimates in long-term time scale. Convolutional Long Short-Term Memory (ConvLSTM), has emerged as a promising approach capable of extracting spatio-temporal features. Hence, we propose a novel composite model named CL-ETAS model, which combines the strengths of ConvLSTM and ETAS model. We conduct experimental verification on real seismic data in Southern California. Our results show that CL-ETAS model outperforms both ETAS model and ConvLstm in accurately forecasting the number of earthquake events, their magnitude, and spatial distribution. Additionally, CL-ETAS model demonstrates notable enhancements in forecast stability and interpretability. These results offer valuable insights and recommendations for future earthquake forecasting endeavors.