EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Bayesian three-dimensional seismic traveltime tomography for active- and passive-source seismic data using physics-informed neural networks

Ryoichiro Agata, Kazuya Shiraishi, Gou Fujie, Dan Bassett

Geophysical Journal International · 08.10.2026 · 247 (3)

DOI: 10.1093/gji/ggag433 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Geophysical Journal International, online erschienen am 09.10.2026. Verfasst von Ryoichiro Agata und 3 weiteren Autor:innen. Die Arbeit nennt 69 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: MEXT, JSPS, JST.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Accurate three-dimensional (3-D) seismic velocity modelling through seismic traveltime tomography using both active- and passive-source data provides critical underpinning models for seismicity monitoring and hazard assessment. Because traveltime tomography is an inherently ill-posed inverse problem, uncertainty quantification (UQ) of the estimated models using Bayesian methods is also important for reliable downstream interpretations and analyses. However, Bayesian inference for 3-D tomography based on conventional grid-based representations faces the ‘curse of dimensionality’ and severe computational bottlenecks. Consequently, rigorous Bayesian UQ for margin-wide 3-D traveltime tomography has remained largely unexplored, despite its importance for reliable interpretation of large-scale velocity models. In this study, we propose a meshless 3-D Bayesian traveltime tomography method that combines physics-informed neural networks (PINNs) with a neural representation of the velocity structure, enabling tractable and data-efficient Bayesian inference through function-space Particle-based Variational Inference (fParVI). To efficiently integrate passive-source data into the Bayesian estimation of the velocity structure, we introduce an analytical marginalization strategy that treats uncertain parameters related to the origin time and location as nuisance parameters, with passive-source relocation carried out in post-processing. We validated the capability of our approach for 3-D problems through synthetic experiments. These experiments demonstrate its robustness against biased prior source locations compared to standard methods that suffer from overfitting. Furthermore, we applied the method to a real-world data set off the Kii Peninsula, Nankai Trough, using over 380 000 traveltime picks from marine active-source surveys and natural earthquakes. Our probabilistic 3-D ensemble successfully resolves key geological features, such as the Kumano Pluton, and provides data-consistent uncertainty maps that offer new quantitative insights into the reliability of previously debated deep low-velocity zones. The posterior mean hypocenters shifted mainly in the vertical direction by 10–15 km, consistent with the deterministic relocation results of a previous study. Finally, the continuous neural representation drastically reduces storage requirements for the entire ensemble velocity model, highlighting the scalability and data efficiency of the proposed framework for Bayesian seismic traveltime tomography.

Förderung

  • MEXT
  • JSPS
  • JST
  • SICORP
  • University of Tokyo
  • JAMSTEC

Zitieren

APA

Agata, R., Shiraishi, K., Fujie, G., & Bassett, D. (2026). Bayesian three-dimensional seismic traveltime tomography for active- and passive-source seismic data using physics-informed neural networks. Geophysical Journal International, 247(3). https://doi.org/10.1093/gji/ggag433

Vancouver

Agata R, Shiraishi K, Fujie G, Bassett D. Bayesian three-dimensional seismic traveltime tomography for active- and passive-source seismic data using physics-informed neural networks. Geophysical Journal International. 2026;247(3). doi:10.1093/gji/ggag433

BibTeX
@article{Agata2026,
  author = {Agata, Ryoichiro and Shiraishi, Kazuya and Fujie, Gou and Bassett, Dan},
  title = {Bayesian three-dimensional seismic traveltime tomography for active- and passive-source seismic data using physics-informed neural networks},
  journal = {Geophysical Journal International},
  year = {2026},
  volume = {247},
  number = {3},
  doi = {10.1093/gji/ggag433}
}
Kostenlos starten →