ACOUSTIC WAVEFORM INVERSION WITH IMAGE-TO-IMAGE SCHRODINGER BRIDGES
- Authors: Stankevich A.S1, Petrov I.B1
-
Affiliations:
- Moscow Institute of Physics and Technology
- Issue: Vol 65, No 8 (2025)
- Pages: 1451–1466
- Section: Computer science
- URL: https://journals.rcsi.science/0044-4669/article/view/308338
- DOI: https://doi.org/10.31857/S0044466925080124
- EDN: https://elibrary.ru/VJWPZG
- ID: 308338
Cite item
Abstract
Recent developments in application of deep learning models to acoustic Full Waveform Inversion (FWI) are marked by the use of diffusion models as prior distributions for Bayesian-like inference procedures. The advantage of these methods is the ability to generate high-resolution samples, which are otherwise unattainable with classical inversion methods or other deep learning-based solutions. However, the iterative and stochastic nature of sampling from diffusion models along with heuristic nature of output control remain limiting factors for their applicability For instance, an optimal way to include the approximate velocity model into diffusion-based inversion scheme remains unclear, even though it is considered an essential part of FWI pipeline. We address the issue by employing a Schrodinger Bridge that interpolates ¨ between the distributions of ground truth and smoothed velocity models. Thus, the inference process that starts from an approximate velocity model is guaranteed to arrive at a sample from the distribution of reference velocity models in a finite time. To facilitate the learning of nonlinear drifts that transfer samples between distributions and to enable controlled inference given the seismic data, we extend the concept of Image-to-Image Schrodinger Bridge (I ¨ 2SB) to conditional sampling, resulting in a conditional Image-to-Image Schrodinger Bridge (cI ¨ 2SB) framework for acoustic inversion. To validate our method, we assess its effectiveness in reconstructing the reference velocity model from its smoothed approximation, coupled with the observed seismic signal of fixed shape. Our experiments demonstrate that the proposed solution outperforms our reimplementation of conditional diffusion model suggested in earlier works, while requiring only a few neural function evaluations (NFEs) to achieve sample fidelity superior to that attained with supervised learning-based approach. The supplementary code implementing the algorithms described in this paper can be found in the repository https://github.com/stankevich-mipt/seismic_inversion_via_
About the authors
A. S Stankevich
Moscow Institute of Physics and Technology
Email: stankevich.as@phystech.edu
I. B Petrov
Moscow Institute of Physics and Technology
Author for correspondence.
Email: stankevich.as@phystech.edu
References
- Russell B.H. Introduction to seismic inversion methods. SEG Books, 1988.
- Schuster G.T. Seismic inversion. Society of Exploration Geophysicists, 2017.
- Robertsson J.O., Bednar B., Blanch J., Kostov C., van Manen D.J. Introduction to the supplement on seismic modeling with applications to acquisition, processing, and interpretation, 2007.
- Adler A., Araya-Polo M., Poggio T. Deep learning for seismic inverse problems: Toward the acceleration of geophysical analysis workflows. IEEE Signal Processing Magazine, vol. 38, no. 2 (2021), pp. 89–119.
- Mousavi S.M., Beroza G.C., Mukerji T., Rasht-Behesht M. Applications of deep neural networks in exploration seismology: A technical survey. Geophysics, vol. 89, no. 1 (2024), pp. WA95–WA115.
- Araya-Polo M., Jennings J., Adler A., Dahlke T. Deep-learning tomography. The Leading Edge, vol. 37, no. 1 (2018), pp. 58–66.
- Zhang W., Gao J., Gao Z., Chen H. Adjoint-driven deep-learning seismic full-waveform inversion. IEEE Transactions on Geoscience and Remote Sensing, vol. 59, no. 10 (2020), pp. 8913–8932.
- Zhang W., Gao J. Deep-learning full-waveform inversion using seismic migration images. IEEE Transactions on Geoscience and Remote Sensing, vol. 60 (2021), pp. 1–18.
- Wu Y., Lin Y. InversionNet: An efficient and accurate data-driven full waveform inversion. IEEE Transactions on Computational Imaging, vol. 6 (2019), pp. 419–433.
- Yang F., Ma J. Deep-learning inversion: A next-generation seismic velocity model building method. Geophysics, vol. 84, no. 4 (2019), pp. R583–R599.
- Zhang Z., Lin Y. Data-driven seismic waveform inversion: A study on the robustness and generalization. IEEE Transactions on Geoscience and Remote sensing, vol. 58, no. 10 (2020), pp. 6900–6913.
- Ho J., Jain A., Abbeel P. Denoising diffusion probabilistic models. Advances in neural information processing systems, vol. 33 (2020), pp. 6840–6851.
- Yang L., Zhang Z., Song Y., Hong S., Xu R., Zhao Y., Zhang W., Cui B., Yang M.H. Diffusion models: A comprehensive survey of methods and applications. ACM Computing Surveys, vol. 56, no. 4 (2023), pp. 1–39.
- Song Y., Sohl-Dickstein J., Kingma D.P., Kumar A., Ermon S., Poole B. Score-based generative modeling through stochastic differential equations. arXiv preprint arXiv:2011.13456.
- Li H., Yang Y., Chang M., Chen S., Feng H., Xu Z., Li Q., Chen Y. Srdiff: Single image super-resolution with diffusion probabilistic models. Neurocomputing, vol. 479 (2022), pp. 47–59.
- Lugmayr A., Danelljan M., Romero A., Yu F., Timofte R., Van Gool L. Repaint: Inpainting using denoising diffusion probabilistic models. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. pp. 11 461–11 471.
- Kawar B., Elad M., Ermon S., Song J. Denoising diffusion restoration models. Advances in Neural Information Processing Systems, vol. 35 (2022), pp. 23 593–23 606.
- Ho J., Salimans T. Classifier-Free Diffusion Guidance, 2022.
- Rombach R., Blattmann A., Lorenz D., Esser P., Ommer B. High-Resolution Image Synthesis with Latent Diffusion Models, 2022.
- Wang F., Huang X., Alkhalifah T.A. IEEE Transactions on Geoscience and Remote Sensing, vol. 61 (2023), p. 1–11. https://doi.org/10.1109/tgrs.2023.3337014.
- Wang F., Huang X., Alkhalifah T. Controllable seismic velocity synthesis using generative diffusion models. Journal of Geophysical Research: Machine Learning and Computation, vol. 1, no. 3 (2024), p. e2024JH000 153.
- Zhang H., Li Y., Huang J. DiffusionVel: Multi-information integrated velocity inversion using generative diffusion models. arXiv preprint arXiv:2410.21776.
- Shi Y., De Bortoli V., Deligiannidis G., Doucet A. Conditional simulation using diffusion Schrodinger bridges. In Uncertainty in Artificial Intelligence. PMLR, pp. 1792–1802.
- Liu G.H., Vahdat A., Huang D.A., Theodorou E.A., Nie W., Anandkumar A. I2SB: Image-to-Image Schrodinger Bridge, 2023.
- Deng C., Feng Y., Feng S., Jin P., Zhang X., Zeng Q., Lin Y. OpenFWI: Benchmark Seismic Datasets for Machine Learning-Based Full Waveform Inversion. CoRR, vol. abs/2111.02926.
- An overview of full-waveform inversion in exploration geophysics. Geophysics, vol. 74, no. 6 (2009), pp. WCC1–WCC26.
- Anderson B.D. Reverse-time diffusion equation models. Stochastic Processes and their Applications, vol. 12, no. 3 (1982), pp. 313–326.
- Vincent P. A connection between score matching and denoising autoencoders. Neural computation, vol. 23, no. 7 (2011), pp. 1661–1674.
- Schrodinger E. Sur la theorie relativiste de l’electron et l’interpretation de la mecanique quantique. In Annales de l’institut Henri Poincare. vol. 2, pp. 269–310.
- Pavon M., Wakolbinger A. On free energy, stochastic control, and Schrodinger processes. In Modeling, Estimation and Control of Systems with Uncertainty: Proceedings of a Conference held in Sopron, Hungary, September 1990. Springer, pp. 334–348.
- Leonard C. A survey of the schr∖"odinger problem and some of its connections with optimal transport. arXiv preprint arXiv:1308.0215.
- Chen Y., Georgiou T.T., Pavon M. Stochastic control liaisons: Richard sinkhorn meets gaspard monge on a schrodinger bridge. Siam Review, vol. 63, no. 2 (2021), pp. 249–313.
- Chen T., Liu G.H., Theodorou E.A. Likelihood training of schr∖"odinger bridge using forward-backward sdes theory. arXiv preprint arXiv:2110.11291.
- De Bortoli V., Thornton J., Heng J., Doucet A. Diffusion schrodinger bridge with applications to score-based generative modeling. Advances in Neural Information Processing Systems, vol. 34 (2021), pp. 17 695–17 709.
- Chen Y., Georgiou T.T., Pavon M. Stochastic control liaisons: Richard Sinkhorn meets Gaspard Monge on a Schroedinger bridge, 2020.
- Brock A., Donahue J., Simonyan K. Large scale GAN training for high fidelity natural image synthesis. arXiv preprint arXiv:1809.11096.
- Dhariwal P., Nichol A. Diffusion Models Beat GANs on Image Synthesis. CoRR, vol. abs/2105.05233.
- Karras T., Aittala M., Aila T., Laine S. Elucidating the Design Space of Diffusion-Based Generative Models, 2022.
- Nichol A., Dhariwal P. Improved Denoising Diffusion Probabilistic Models. CoRR, vol. abs/2102.09672.
- Song J., Meng C., Ermon S. Denoising diffusion implicit models. arXiv preprint arXiv:2010.02502.
- Jin P., Feng Y., Feng S., Wang H., Chen Y., Consolvo B., Liu Z., Lin Y. An empirical study of large-scale data-driven full waveform inversion. Scientific Reports, vol. 14, no. 1 (2024), p. 20 034.
Supplementary files
