A prior regularized full waveform inversion using generative diffusion models

TL;DR

This paper introduces a novel FWI regularization technique using generative diffusion models, enabling high-quality subsurface imaging even with sparse or noisy data by incorporating prior models into the inversion process.

Contribution

The authors develop a new FWI regularization framework using pre-trained generative diffusion models, improving reconstruction quality under limited or noisy observations.

Findings

Outperforms conventional FWI with negligible additional computational cost.

Effective in reconstructing high-quality models from sparse or noisy data.

Demonstrated success on both numerical simulations and field data.

Abstract

Full waveform inversion (FWI) has the potential to provide high-resolution subsurface model estimations. However, due to limitations in observation, e.g., regional noise, limited shots or receivers, and band-limited data, it is hard to obtain the desired high-resolution model with FWI. To address this challenge, we propose a new paradigm for FWI regularized by generative diffusion models. Specifically, we pre-train a diffusion model in a fully unsupervised manner on a prior velocity model distribution that represents our expectations of the subsurface and then adapt it to the seismic observations by incorporating the FWI into the sampling process of the generative diffusion models. What makes diffusion models uniquely appropriate for such an implementation is that the generative process retains the form and dimensions of the velocity model. Numerical examples demonstrate that our method can outperform the conventional FWI with only negligible additional computational cost. Even in cases of very sparse observations or observations with strong noise, the proposed method could still reconstruct a high-quality subsurface model. Thus, we can incorporate our prior expectations of the solutions in an efficient manner. We further test this approach on field data, which demonstrates the effectiveness of the proposed method.