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: 27 works
Citation information provided by
Web of Science

Save / Share:

Works referenced in this record:

Non-volcanic tremor and low-frequency earthquake swarms
journal, March 2007

  • Shelly, David R.; Beroza, Gregory C.; Ide, Satoshi
  • Nature, Vol. 446, Issue 7133
  • DOI: 10.1038/nature05666

Acoustic emission and microslip precursors to stick-slip failure in sheared granular material: AE AND MICROSLIP PRECURSORS
journal, November 2013

  • Johnson, P. A.; Ferdowsi, B.; Kaproth, B. M.
  • Geophysical Research Letters, Vol. 40, Issue 21
  • DOI: 10.1002/2013GL057848

Large Earthquake Occurrence Estimation Based on Radial Basis Function Neural Networks
journal, September 2014

  • Alexandridis, Alex; Chondrodima, Eva; Efthimiou, Evangelos
  • IEEE Transactions on Geoscience and Remote Sensing, Vol. 52, Issue 9
  • DOI: 10.1109/TGRS.2013.2288979

Tidal triggering of earthquakes suggests poroelastic behavior on the San Andreas Fault
journal, February 2017

  • Delorey, Andrew A.; van der Elst, Nicholas J.; Johnson, Paul A.
  • Earth and Planetary Science Letters, Vol. 460
  • DOI: 10.1016/j.epsl.2016.12.014

Earthquake Forecasting Using Neural Networks: Results and Future Work
journal, June 2006


Potential slab deformation and plunge prior to the Tohoku, Iquique and Maule earthquakes
journal, April 2016

  • Bouchon, Michel; Marsan, David; Durand, Virginie
  • Nature Geoscience, Vol. 9, Issue 5
  • DOI: 10.1038/ngeo2701

The IASPEI procedure for the evaluation of earthquake precursors
journal, December 1997


Three-dimensional discrete element modeling of triggered slip in sheared granular media
journal, April 2014


Nonvolcanic Deep Tremor Associated with Subduction in Southwest Japan
journal, May 2002


The long precursory phase of most large interplate earthquakes
journal, March 2013

  • Bouchon, Michel; Durand, Virginie; Marsan, David
  • Nature Geoscience, Vol. 6, Issue 4
  • DOI: 10.1038/ngeo1770

Acoustic emissions document stress changes over many seismic cycles in stick-slip experiments: AEs DOCUMENT STRESS CHANGES
journal, May 2013

  • W. Goebel, T. H.; Schorlemmer, D.; Becker, T. W.
  • Geophysical Research Letters, Vol. 40, Issue 10
  • DOI: 10.1002/grl.50507

Earthquake prediction: a critical review
journal, December 1997


Fault behavior and characteristic earthquakes: Examples from the Wasatch and San Andreas Fault Zones
journal, July 1984

  • Schwartz, David P.; Coppersmith, Kevin J.
  • Journal of Geophysical Research: Solid Earth, Vol. 89, Issue B7
  • DOI: 10.1029/JB089iB07p05681

On the micromechanics of slip events in sheared, fluid-saturated fault gouge: Stick-Slip Dynamics in Saturated Gouge
journal, June 2017

  • Dorostkar, Omid; Guyer, Robert A.; Johnson, Paul A.
  • Geophysical Research Letters, Vol. 44, Issue 12
  • DOI: 10.1002/2017GL073768

Deep low-frequency earthquakes in tremor localize to the plate interface in multiple subduction zones
journal, January 2009

  • Brown, Justin R.; Beroza, Gregory C.; Ide, Satoshi
  • Geophysical Research Letters, Vol. 36, Issue 19
  • DOI: 10.1029/2009GL040027

Correlation and variable importance in random forests
journal, March 2016

  • Gregorutti, Baptiste; Michel, Bertrand; Saint-Pierre, Philippe
  • Statistics and Computing, Vol. 27, Issue 3
  • DOI: 10.1007/s11222-016-9646-1

Crossover behavior in failure avalanches
journal, July 2006


Two categories of earthquake precursors, physical and tectonic, and their roles in intermediate-term earthquake prediction
journal, June 1988

  • Ishibashi, Katsuhiko
  • Pure and Applied Geophysics PAGEOPH, Vol. 126, Issue 2-4
  • DOI: 10.1007/BF00879015

Frictional strength and strain weakening in simulated fault gouge: Competition between geometrical weakening and chemical strengthening
journal, January 2010

  • Niemeijer, André; Marone, Chris; Elsworth, Derek
  • Journal of Geophysical Research, Vol. 115, Issue B10
  • DOI: 10.1029/2009JB000838

GEOPHYSICS: Enhanced: Slow But Not Quite Silent
journal, June 2003


Intermediate-term prediction of occurrence times of strong earthquakes
journal, October 1988

  • Keilis-Borok, V. I.; Knopoff, L.; Rotwain, I. M.
  • Nature, Vol. 335, Issue 6192
  • DOI: 10.1038/335690a0

The debate on the prognostic value of earthquake foreshocks: A meta-analysis
journal, February 2014


The Parkfield, California, Earthquake Prediction Experiment
journal, August 1985


Deep-Focus Earthquake Analogs Recorded at High Pressure and Temperature in the Laboratory
journal, September 2013


Laboratory-Derived Friction laws and Their Application to Seismic Faulting
journal, May 1998


Random Forests
journal, January 2001


Predictability of repeating earthquakes near Parkfield, California: Parkfield microrepeater predictability
journal, April 2012


    Works referencing / citing this record:

    Machine Learning Can Predict the Timing and Size of Analog Earthquakes
    journal, February 2019

    • Corbi, F.; Sandri, L.; Bedford, J.
    • Geophysical Research Letters, Vol. 46, Issue 3
    • DOI: 10.1029/2018gl081251

    Machine Learning Can Predict the Timing and Size of Analog Earthquakes
    journal, February 2019

    • Corbi, F.; Sandri, L.; Bedford, J.
    • Geophysical Research Letters, Vol. 46, Issue 3
    • DOI: 10.1029/2018gl081251