Metraipolis › archive › dc_51b7ff7364da
Structure-aware Bayesian full waveform inversion via diffusion-regularized Stein variational gradient descent — arXiv:2610.19187
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.19187
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-15T14:23:17.307Z
- SHA-256 of the archived text
3e727201ed92b28f04c82960312e3d3c9f2b08d42223eeb8deb84a79f289cf25- Stable URL of this page
https://metraipolis.com/documento/dc_51b7ff7364da
How to cite
Structure-aware Bayesian full waveform inversion via diffusion-regularized Stein variational gradient descent — arXiv:2610.19187 — arXiv (en), https://arxiv.org/abs/2610.19187 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_51b7ff7364da (Metraipolis archive dc_51b7ff7364da, sha256 3e727201ed92b28f04c82960312e3d3c9f2b08d42223eeb8deb84a79f289cf25)
BibTeX
@misc{dc51b7ff7364da,
title = {Structure-aware Bayesian full waveform inversion via diffusion-regularized Stein variational gradient descent — arXiv:2610.19187},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.19187},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_51b7ff7364da; sha256 3e727201ed92b28f04c82960312e3d3c9f2b08d42223eeb8deb84a79f289cf25},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.19187. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Full waveform inversion (FWI) is a powerful tool for high-resolution subsurface model reconstruction, but it remains highly nonlinear and ill-posed, especially when the initial model is inaccurate or the acquired data are noisy and incomplete. Annealed Stein variational gradient descent (ASVGD) provides a particle-based Bayesian framework for FWI by approximating the posterior distribution with an ensemble of velocity models, thereby enabling uncertainty quantification beyond a single deterministic solution. However, conventional ASVGD-FWI commonly relies on simple handcrafted priors, such as Gaussian or smoothing assumptions, which are often insufficient to represent complex geological structures. To address this limitation, we introduce a learned diffusion model (DM) as an implicit regularization mechanism within the ASVGD-FWI framework. Instead of explicitly evaluating the diffusion prior density, the trained diffusion model acts as a learned geological projection operator that guides updated particles toward the distribution of plausible velocity models. In this way, the proposed method combines data consistency from FWI, posterior diversity from ASVGD, and structural realism from the diffusion prior. Numerical experiments demonstrate that the diffusion-regularized ASVGD-FWI produces more geologically consistent mean models, suppresses nonphysical artifacts, and yields uncertainty estimates that are more concentrated around structurally complex and poorly constrained regions. These results suggest that learned diffusion priors can effectively enhance Bayesian FWI by improving both inversion stability and the interpretability of posterior uncertainty. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno). Categorie arXiv: Machine Learning (stat.ML) ; Machine Learning (cs.LG); Geophysics (physics.geo-ph). Pagina del lavoro: https://arxiv.org/abs/2610.19187 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-15T13:53:35.838Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).