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

• Published in: Communications Earth & Environment
• Main Authors: Monterrubio Velasco, Marisol, Callaghan, Scott, Modesto Galende, David, Carrasco Jiménez, José Carlos, Badia Sala, Rosa Maria, Pallarés Font de Mora, Pablo, Vázquez Novoa, Fernando, Quintana Ortí, Enrique Salvador, Pienkowska, Marta, de la Puente, Josep
• Other Authors: Universitat Politècnica de Catalunya. Departament d'Arquitectura de Computadors, Universitat Politècnica de Catalunya. Doctorat en Arquitectura de Computadors, Barcelona Supercomputing Center
• Format: Article in Journal/Newspaper
• Language: English
• Published: Nature 2024
• Subjects: Àrees temàtiques de la UPC::Informàtica::Intel·ligència artificial::Aprenentatge automàtic; Àrees temàtiques de la UPC::Enginyeria civil::Geotècnia::Sismologia; Earthquakes; Machine learning; Terratrèmols; Aprenentatge automàtic; Iceland
• Online Access: http://hdl.handle.net/2117/408851; https://doi.org/10.1038/s43247-024-01436-1

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. This work has been funded by the European Commission’s Horizon 2020 Framework program and the European High-Performance Computing Joint Undertaking (JU) under grant agreement No 955558 and by MCIN/AEI/ 10.13039/501100011033 and the European Union NextGeneration EU/PRTR(PCI2021-121957), project eFlows4HPC. This research has been supported by the European High-Performance Computing Joint Undertaking (JU) as well as Spain, Italy, Iceland, Germany, Norway, France, Finland, and Croatia under grant agreement no. 101093038, (ChEESE-CoE). The authors acknowledge the Center for Advanced Research Computing (CARC) at the University of Southern California for providing computing resources that have contributed to the research results reported within this publication. URL: https://carc.usc.edu. This research used resources of the Oak Ridge Leadership Computing Facility, which is a DOE Office of Science User Facility supported under Contract ...