What question did this study set out to answer?

The research aims to develop a model that predicts earthquake ground motions more accurately than traditional methods.

March 18, 2026Nature CommunicationsOpen Access

Learning earthquake ground motions via conditional generative modeling

View Full Paper

Ask AI

Bookmark

Authors

PRPu RenLawrence Berkeley National Laboratory RNRie NakataInternational Computer Science Institute MLMaxime LacourInternational Computer Science Institute

Discussion

Member takes

Implication

Demonstrates the effectiveness of CGM-GM in predicting ground motions for seismic hazard assessment, highlighting its implications for infrastructure resilience.

Key Points

The research aims to develop a model that predicts earthquake ground motions more accurately than traditional methods.
Proposed a conditional generative model (CGM-GM) using AI for ground motion prediction.
Inputs include earthquake magnitudes, geographic coordinates, and sensor data.
Utilized a probabilistic autoencoder for extracting latent distributions in time-frequency space.
Implemented variational sequential models for prior and posterior distributions.
CGM-GM shows potential to complement physics-based simulations.
Demonstrated effectiveness in predicting spatially continuous Fourier amplitude spectra.
Reported promising outcomes for small-magnitude earthquakes in a seismically risky region.

Cite This Study

Ren et al. (2026) studied this question.

synapsesocial.com/papers/69ba424e4e9516ffd37a261a https://doi.org/10.1038/s41467-026-70719-2

View Full Paper

Ask AI

Bookmark

Implication

Demonstrates the effectiveness of CGM-GM in predicting ground motions for seismic hazard assessment, highlighting its implications for infrastructure resilience.

Learning earthquake ground motions via conditional generative modeling

Discussion

Member takes

Implication

Key Points

Cite This Study

Learning earthquake ground motions via conditional generative modeling

Discussion

Member takes

Implication

Key Points

Cite This Study

Also Consider

Also Consider