Deep learning for laboratory earthquake prediction and autoregressive forecasting of fault zone stress

作者：Laura Laurenti, E. Tinti, Fabio Galasso, Luca Franco, C. Marone · 发表于：Earth and Planetary Science Letters · 年份：2022 · DOI：10.1016/j.epsl.2022.117825 · 被引用次数：81 · 研究领域：Computer Science、Physics

Earthquake forecasting and prediction have long and in some cases sordid histories but recent work has rekindled interest based on advances in early warning, hazard assess-ment for induced seismicity and successful prediction of laboratory earthquakes. In the lab, frictional stick-slip events provide an analog for earthquakes and the seismic cycle. Labquakes are also ideal targets for machine learning (ML) because they can be produced in long sequences under controlled conditions. Indeed, recent works show that ML can predict several aspects of labquakes using fault zone acoustic emissions (AE). Here, we generalize these results and explore deep learning (DL) methods for labquake prediction and autoregressive (AR) forecasting. The AR methods allow forecasting at future horizons via iterative predictions. We address questions of whether DL methods can outperform existing ML models, including prediction based on limited training or forecasts beyond a single seismic cycle for aperiodic failure. We describe significant improvements to existing methods of labquake prediction. We demonstrate: 1) that DL models based on Long-Short Term Memory and Convolution Neural Networks predict labquakes under several conditions, including pre-seismic creep, aperiodic events and alternating slow/fast events and 2) that fault zone stress can be predicted with fidelity, confirming that acoustic energy is a fingerprint of fault zone stress. We predict also time to start of failure (TTsF) and time to th...