Machine Learning Predicts the Timing and Shear Stress Evolution of Lab Earthquakes Using Active Seismic Monitoring of Fault Zone Processes

Journal Article · 18 July 2021 · Journal of Geophysical Research. Solid Earth

DOI: https://doi.org/10.1029/2020JB021588 · OSTI ID:1808621

Shreedharan, Srisharan  ^[1]; Bolton, David Chas  ^[2]; Rivière, Jacques ^[3]; Marone, Chris  ^[4]

---

1. Department of Geosciences Pennsylvania State University University Park USA, Now at The University of Texas Institute for Geophysics Austin USA
2. Department of Geosciences Pennsylvania State University University Park USA
3. Department of Engineering Science and Mechanics Pennsylvania State University University Park USA
4. Department of Geosciences Pennsylvania State University University Park USA, Dipartimento di Scienze della Terra La Sapienza Università di Roma Italy

Abstract Machine learning (ML) techniques have become increasingly important in seismology and earthquake science. Lab‐based studies have used acoustic emission data to predict time‐to‐failure and stress state, and in a few cases, the same approach has been used for field data. However, the underlying physical mechanisms that allow lab earthquake prediction and seismic forecasting remain poorly resolved. Here, we address this knowledge gap by coupling active‐source seismic data, which probe asperity‐scale processes, with ML methods. We show that elastic waves passing through the lab fault zone contain information that can predict the full spectrum of labquakes from slow slip instabilities to highly aperiodic events. The ML methods utilize systematic changes in P‐wave amplitude and velocity to accurately predict the timing and shear stress during labquakes. The ML predictions improve in accuracy closer to fault failure, demonstrating that the predictive power of the ultrasonic signals improves as the fault approaches failure. Our results demonstrate that the relationship between the ultrasonic parameters and fault slip rate, and in turn, the systematically evolving real area of contact and asperity stiffness allow the gradient boosting algorithm to “learn” about the state of the fault and its proximity to failure. Broadly, our results demonstrate the utility of physics‐informed ML in forecasting the imminence of fault slip at the laboratory scale, which may have important implications for earthquake mechanics in nature.

• Research Organization: Pennsylvania State University, University Park, PA (United States)
• Sponsoring Organization: European Research Council; National Science Foundation (NSF); USDOE; USDOE Office of Energy Efficiency and Renewable Energy (EERE), Renewable Power Office. Geothermal Technologies Office; USDOE Office of Science (SC)
• Grant/Contract Number: EE0008763; SC0020512
• OSTI ID: 1808621
• Journal Information: Journal of Geophysical Research. Solid Earth, Journal Name: Journal of Geophysical Research. Solid Earth Journal Issue: 7 Vol. 126; ISSN 2169-9313
• Publisher: American Geophysical Union (AGU)Copyright Statement
• Country of Publication: United States
• Language: English