Laboratory earthquake forecasting: A machine learning competition

Proceedings of the National Academy of Sciences, vol. 118

Abstract

Earthquake prediction, the long-sought holy grail of earthquake science, continues to confound Earth scientists. Could we make advances by crowdsourcing, drawing from the vast knowledge and creativity of the machine learning (ML) community? We used Google's ML competition platform, Kaggle, to engage the worldwide ML community with a competition to develop and improve data analysis approaches on a forecasting problem that uses laboratory earthquake data. The competitors were tasked with predicting the time remaining before the next earthquake of successive laboratory quake events, based on only a small portion of the laboratory seismic data. The more than 4,500 participating teams created and shared more than 400 computer programs in openly accessible notebooks. Complementing the now well-known features of seismic data that map to fault criticality in the laboratory, the winning teams employed unexpected strategies based on rescaling failure times as a fraction of the seismic cycle and comparing input distribution of training and testing data. In addition to yielding scientific insights into fault processes in the laboratory and their relation with the evolution of the statistical properties of the associated seismic data, the competition serves as a pedagogical tool for teaching ML in geophysics. The approach may provide a model for other competitions in geosciences or other domains of study to help engage the ML community on problems of significance.

Authors 13

1. Paul Allan Johnson corresponding

   Los Alamos National Laboratory

   Affiliation as printed

   Geophysics Group, Los Alamos National Laboratory, Los Alamos, NM 87545;

2. Bertrand Rouet‐Leduc

   Los Alamos National Laboratory

   Affiliation as printed

   Geophysics Group, Los Alamos National Laboratory, Los Alamos, NM 87545;

3. L. J. Pyrak‐Nolte

   Purdue University West Lafayette

   Affiliation as printed

   Department of Earth, Atmospheric and Planetary Sciences, Purdue University, West Lafayette, IN 47907;

   Department of Physics and Astronomy, Purdue University, West Lafayette, IN 47907;

   Lyles School of Civil Engineering, Purdue University, West Lafayette, IN 47907;

4. Gregory C. Beroza

   Stanford University

   Affiliation as printed

   Department of Geophysics, Stanford University, Stanford, CA 94305;

5. Chris J. Marone

   Pennsylvania State University · Sapienza University of Rome

   Affiliation as printed

   Department of Earth Science, La Sapienza Università di Roma, 00413 Rome, Italy;

   Department of Earth Science, Pennsylvania State University, University Park, PA 16802;

   Department of Earth Science, Pennsylvania State University, University Park, PA 16802

6. Claudia Hulbert

   Centre National de la Recherche Scientifique · École Normale Supérieure - PSL · Laboratoire de Géologie de l’École Normale Supérieure

   Affiliation as printed

   Laboratoire de Géologie, Département de Géosciences, École Normale Supérieure, PSL University, CNRS UMR, 8538 Paris, France;

7. Addison Howard
   Affiliation as printed

   Kaggle, Google, LLC, Denver, CO 80301;

8. Philipp Singer
   Affiliation as printed

   H2O.ai, 1010 Vienna, Austria;

9. Dimosthenis Karaflos
   Affiliation as printed

   Private individual, Athens 11364, Greece;

10. Corey James Levinson
    Affiliation as printed

    Private individual, Jacksonville, FL, 32207;

11. Pascal Pfeiffer Aachen Department of Electrical Engineering

    RWTH Aachen University

    Affiliation as printed

    Department of Electrical Engineering, Rheinisch-Westfälische Technische Hochschule Aachen University, 52056 Aachen, Germany;

12. Kin Ming Puk
    Affiliation as printed

    Private individual, Bethesda, MD 20817

13. Walter Reade
    Affiliation as printed

    Kaggle, Google, LLC, Denver, CO 80301;