Machine Learning Predicts Laboratory Earthquakes

TL;DR

This study demonstrates that machine learning analyzing acoustic signals from laboratory faults can accurately predict failure times, revealing previously overlooked signals and offering potential advancements in earthquake forecasting.

Contribution

The paper introduces a novel machine learning approach that predicts fault failure times using only instantaneous acoustic signals, without relying on historical data.

Findings

Machine learning accurately predicts laboratory fault failure times.

Identifies previously overlooked low-amplitude signals associated with fault failure.

Suggests potential for applying this method to real seismic data for earthquake forecasting.

Abstract

Forecasting fault failure is a fundamental but elusive goal in earthquake science. Here we show that by listening to the acoustic signal emitted by a laboratory fault, machine learning can predict the time remaining before it fails with great accuracy. These predictions are based solely on the instantaneous physical characteristics of the acoustical signal, and do not make use of its history. Surprisingly, machine learning identifies a signal emitted from the fault zone previously thought to be low-amplitude noise that enables failure forecasting throughout the laboratory quake cycle. We hypothesize that applying this approach to continuous seismic data may lead to significant advances in identifying currently unknown signals, in providing new insights into fault physics, and in placing bounds on fault failure times.