skip to main content
DOE PAGES title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Machine Learning Predicts Laboratory Earthquakes

Abstract

Here, we apply machine learning to data sets from shear laboratory experiments, with the goal of identifying hidden signals that precede earthquakes. 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 infer that this signal originates from continuous grain motions of the fault gouge as the fault blocks displace. We posit 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.

Authors:
 [1];  [2];  [3];  [2];  [4]; ORCiD logo [2]
  1. Los Alamos National Lab. (LANL), Los Alamos, NM (United States); Univ. of Cambridge, Cambridge (United Kingdom)
  2. Los Alamos National Lab. (LANL), Los Alamos, NM (United States)
  3. Los Alamos National Lab. (LANL), Los Alamos, NM (United States); Boston Univ., Boston, MA (United States)
  4. Univ. of Cambridge, Cambridge (United Kingdom)
Publication Date:
Research Org.:
Los Alamos National Lab. (LANL), Los Alamos, NM (United States)
Sponsoring Org.:
USDOE Laboratory Directed Research and Development (LDRD) Program
OSTI Identifier:
1460625
Report Number(s):
LA-UR-16-26108
Journal ID: ISSN 0094-8276
Grant/Contract Number:  
AC52-06NA25396
Resource Type:
Accepted Manuscript
Journal Name:
Geophysical Research Letters
Additional Journal Information:
Journal Volume: 44; Journal Issue: 18; Journal ID: ISSN 0094-8276
Publisher:
American Geophysical Union
Country of Publication:
United States
Language:
English
Subject:
58 GEOSCIENCES; Earth Sciences; Energy Sciences; Material Science; earthquake forecasting; critical stress state; brittle failure; machine learning; earthquake prediction; laboratory earthquake; acoustic signal identification; earthquake precursors

Citation Formats

Rouet-Leduc, Bertrand, Hulbert, Claudia, Lubbers, Nicholas, Barros, Kipton, Humphreys, Colin J., and Johnson, Paul Allan. Machine Learning Predicts Laboratory Earthquakes. United States: N. p., 2017. Web. doi:10.1002/2017GL074677.
Rouet-Leduc, Bertrand, Hulbert, Claudia, Lubbers, Nicholas, Barros, Kipton, Humphreys, Colin J., & Johnson, Paul Allan. Machine Learning Predicts Laboratory Earthquakes. United States. doi:10.1002/2017GL074677.
Rouet-Leduc, Bertrand, Hulbert, Claudia, Lubbers, Nicholas, Barros, Kipton, Humphreys, Colin J., and Johnson, Paul Allan. Wed . "Machine Learning Predicts Laboratory Earthquakes". United States. doi:10.1002/2017GL074677. https://www.osti.gov/servlets/purl/1460625.
@article{osti_1460625,
title = {Machine Learning Predicts Laboratory Earthquakes},
author = {Rouet-Leduc, Bertrand and Hulbert, Claudia and Lubbers, Nicholas and Barros, Kipton and Humphreys, Colin J. and Johnson, Paul Allan},
abstractNote = {Here, we apply machine learning to data sets from shear laboratory experiments, with the goal of identifying hidden signals that precede earthquakes. 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 infer that this signal originates from continuous grain motions of the fault gouge as the fault blocks displace. We posit 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.},
doi = {10.1002/2017GL074677},
journal = {Geophysical Research Letters},
number = 18,
volume = 44,
place = {United States},
year = {2017},
month = {8}
}

Journal Article:
Free Publicly Available Full Text
Publisher's Version of Record

Citation Metrics:
Cited by: 6 works
Citation information provided by
Web of Science

Save / Share:

Works referenced in this record:

Random Forests
journal, January 2001