A machine learning estimator trained on synthetic data for real-time earthquake ground-shaking predictions in Southern California (in EN)
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
Real-Time Fault Tracking and Ground Motion Prediction for Large Earthquakes With HR-GNSS and Deep Learning
Instantaneous tracking of earthquake growth with elastogravity signals