Learning Physics for Unveiling Hidden Earthquake Ground Motions via Conditional Generative Modeling
This addresses seismic hazard assessment for infrastructure resilience, offering a novel AI-based approach that is incremental in improving simulation methods.
The paper tackles the problem of predicting high-fidelity earthquake ground motions by proposing CGM-GM, a conditional generative model that synthesizes waveforms using earthquake magnitudes and geographic coordinates, demonstrating strong potential to outperform a state-of-the-art empirical model in the San Francisco Bay Area.
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 a novel artificial intelligence (AI) simulator, Conditional Generative Modeling for Ground Motion (CGM-GM), to synthesize high-frequency and spatially continuous earthquake ground motion waveforms. CGM-GM leverages earthquake magnitudes and geographic coordinates of earthquakes and sensors as inputs, learning complex wave physics and Earth heterogeneities, without explicit physics constraints. This is achieved through a probabilistic autoencoder that captures 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. CGM-GM demonstrates a strong potential for outperforming a state-of-the-art non-ergodic empirical ground motion model and shows great promise in seismology and beyond.