English

Robust Physics-Guided Diffusion for Full-Waveform Inversion

Numerical Analysis 2026-03-18 v1 Artificial Intelligence Numerical Analysis

Abstract

We develop a robust physics-guided diffusion framework for full-waveform inversion that combines a score-based generative prior with likelihood guidance computed through wave-equation simulations. We adopt a transport-based data-consistency potential (Wasserstein-2), incorporating wavefield enhancement via bounded weighting and observation-dependent normalization, thereby improving robustness to amplitude imbalance and time/phase misalignment. On the inference side, we introduce a preconditioned guided reverse-diffusion scheme that adapts the guidance strength and spatial scaling throughout the reverse-time dynamics, yielding a more stable and effective data-consistency guidance step than standard diffusion posterior sampling (DPS). Numerical experiments on OpenFWI datasets demonstrate improved reconstruction quality over deterministic optimization baselines and standard DPS under comparable computational budgets.

Keywords

Cite

@article{arxiv.2603.16393,
  title  = {Robust Physics-Guided Diffusion for Full-Waveform Inversion},
  author = {Jishen Peng and Enze Jiang and Zheng Ma and Xiongbin Yan},
  journal= {arXiv preprint arXiv:2603.16393},
  year   = {2026}
}
R2 v1 2026-07-01T11:24:00.341Z