DOE OSTI · 3375649
Learning earthquake ground motions via conditional generative modeling
Abstract
Predicting high-fidelity ground motions for future earthquakes is crucial for seismic hazard assessment and infrastructure resilience. Conventional empirical simulations suffer from sparse sensor distribution and geographically localized earthquake locations, while physics-based methods are computationally intensive and require accurate representations of Earth structures and earthquake sources. We propose an artificial intelligence (AI) spectrogram generator, Conditional Generative Modeling for Ground Motion (CGM-GM). CGM-GM leverages earthquake magnitudes and geographic coordinates of earthquakes and sensors as inputs, when postprocessed with phase information, capturing spatially continuous Fourier amplitude spectra (FAS) as well as properties such as P and S arrivals, and waveform durations, without explicit physics constraints. This is achieved through a probabilistic autoencoder that extracts latent distributions in the time-frequency domain and variational sequential models for prior and posterior distributions. We evaluate the performance of CGM-GM using small-magnitude earthquake records from the San Francisco Bay Area, a region with high seismic risks. Here, we report that CGM-GM demonstrates potential for complementing physics-based simulations and non-ergodic empirical ground motion models, as well as shows promise in seismology and beyond.
Explore related subjects
Keep this discovery
Explore connections, maps & timelines
Ren, Pu [Lawrence Berkeley National Laboratory (LBNL), Berkeley, CA (United States)] (ORCID:000000026354385X), Nakata, Rie [Lawrence Berkeley National Laboratory (LBNL), Berkeley, CA (United States); Univ. of Tokyo (Japan); University of California, Berkeley, CA (United States). International Computer Science Inst.] (ORCID:0000000291889030), Lacour, Maxime [University of California, Berkeley, CA (United States). International Computer Science Inst.] (ORCID:0000000283164435), Naiman, Ilan [Ben Gurion Univ. of the Negev, Beer Sheva (Israel)], Nakata, Nori [Lawrence Berkeley National Laboratory (LBNL), Berkeley, CA (United States); University of California, Berkeley, CA (United States). International Computer Science Inst.; Massachusetts Inst. of Technology (MIT), Cambridge, MA (United States)] (ORCID:0000000292959416), Song, Jialin [University of California, Berkeley, CA (United States). International Computer Science Inst.; Simon Fraser Univ., Burnaby, BC (Canada)] (ORCID:0009000313816754), Bi, Zhengfa [Lawrence Berkeley National Laboratory (LBNL), Berkeley, CA (United States)], Malik, Osman Asif [Lawrence Berkeley National Laboratory (LBNL), Berkeley, CA (United States)] (ORCID:000000034477481X), Morozov, Dmitriy [Lawrence Berkeley National Laboratory (LBNL), Berkeley, CA (United States)], Azencot, Omri [University of California, Berkeley, CA (United States). International Computer Science Inst.; Ben Gurion Univ. of the Negev, Beer Sheva (Israel)], Erichson, N. Benjamin [Lawrence Berkeley National Laboratory (LBNL), Berkeley, CA (United States); University of California, Berkeley, CA (United States). International Computer Science Inst.] (ORCID:0000000306673516), Mahoney, Michael W. [Lawrence Berkeley National Laboratory (LBNL), Berkeley, CA (United States); University of California, Berkeley, CA (United States). International Computer Science Inst.] (ORCID:0000000179204652). 2026-03-16. Learning earthquake ground motions via conditional generative modeling. https://doi.org/10.1038/s41467-026-70719-2
Cite the original work for its findings. Save a collection to share your selection of sources.