Large-Scale 3D Ground-Motion Synthesis with Physics-Inspired Latent Operator Flow Matching
Abstract
Earthquake hazard analysis and design of spatially distributed infrastructure, such as power grids and energy pipeline networks, require scenario-specific ground-motion time histories with realistic frequency content and spatiotemporal coherence. However, producing the large ensembles needed for uncertainty quantification with physics-based simulations is computationally intensive and impractical for engineering workflows. To address this challenge, we introduce Ground-Motion Flow (GMFlow), a physics-inspired latent operator flow matching framework that generates realistic, large-scale regional ground-motion time-histories conditioned on physical parameters. Validated on simulated earthquake scenarios in the San Francisco Bay Area, GMFlow generates spatially coherent ground motion across more than 9 million grid points in seconds, achieving a 10,000-fold speedup over the simulation workflow, which opens a path toward rapid and uncertainty-aware hazard assessment for distributed infrastructure. More broadly, GMFlow advances mesh-agnostic functional generative modeling and could potentially be extended to the synthesis of large-scale spatiotemporal physical fields in diverse scientific domains.
Keywords
Cite
@article{arxiv.2603.17403,
title = {Large-Scale 3D Ground-Motion Synthesis with Physics-Inspired Latent Operator Flow Matching},
author = {Yaozhong Shi and Grigorios Lavrentiadis and Konstantinos Tsalouchidis and Zachary E. Ross and David McCallen and Caifeng Zou and Kamyar Azizzadenesheli and Domniki Asimaki},
journal= {arXiv preprint arXiv:2603.17403},
year = {2026}
}