Skip to main content
U.S. Department of Energy
Office of Scientific and Technical Information

A machine learning estimator trained on synthetic data for real-time earthquake ground-shaking predictions in Southern California (in EN)

Journal Article · · Communications Earth & Environment

Abstract

After large-magnitude earthquakes, a crucial task for impact assessment is to rapidly and accurately estimate the ground shaking in the affected region. To satisfy real-time constraints, intensity measures are traditionally evaluated with empirical Ground Motion Models that can drastically limit the accuracy of the estimated values. As an alternative, here we present Machine Learning strategies trained on physics-based simulations that require similar evaluation times. We trained and validated the proposed Machine Learning-based Estimator for ground shaking maps with one of the largest existing datasets (<100M simulated seismograms) from CyberShake developed by the Southern California Earthquake Center covering the Los Angeles basin. For a well-tailored synthetic database, our predictions outperform empirical Ground Motion Models provided that the events considered are compatible with the training data. Using the proposed strategy we show significant error reductions not only for synthetic, but also for five real historical earthquakes, relative to empirical Ground Motion Models.

Research Organization:
Oak Ridge National Laboratory (ORNL), Oak Ridge, TN (United States). Oak Ridge Leadership Computing Facility (OLCF)
Sponsoring Organization:
USDOE
Grant/Contract Number:
AC05-00OR22725
OSTI ID:
2581921
Journal Information:
Communications Earth & Environment, Journal Name: Communications Earth & Environment Journal Issue: 1 Vol. 5; ISSN 2662-4435
Publisher:
Springer NatureCopyright Statement
Country of Publication:
United States
Language:
EN

Similar Records

Validation of earthquake ground-motion models in southern California, USA, using precariously balanced rocks
Journal Article · Mon Dec 19 23:00:00 EST 2022 · Geological Society of America, Bulletin · OSTI ID:2424290

Real-Time Fault Tracking and Ground Motion Prediction for Large Earthquakes With HR-GNSS and Deep Learning
Journal Article · Thu Dec 07 23:00:00 EST 2023 · Journal of Geophysical Research. Solid Earth · OSTI ID:2246707

Instantaneous tracking of earthquake growth with elastogravity signals
Journal Article · Wed May 11 00:00:00 EDT 2022 · Nature (London) · OSTI ID:2310321