WISE: Full-waveform variational inference via subsurface extensions-Reference-Cited by-同舟云学术

WISE: Full-waveform variational inference via subsurface extensions

Published:2024-05-31 Issue:4 Volume:89 Page:A23-A28
ISSN:0016-8033
Container-title:GEOPHYSICS
language:en
Short-container-title:GEOPHYSICS

Author:

Yin Ziyi¹^ORCID,Orozco Rafael²^ORCID,Louboutin Mathias³^ORCID,Herrmann Felix J.²

Affiliation:

1. Georgia Institute of Technology, School of Computational Science and Engineering, Atlanta, Georgia, USA. (corresponding author)

2. Georgia Institute of Technology, School of Computational Science and Engineering, Atlanta, Georgia, USA.

3. Devito Codes Ltd, Atlanta, Georgia, USA.

Abstract

We introduce a probabilistic technique for full-waveform inversion, using variational inference and conditional normalizing flows to quantify uncertainty in migration-velocity models and its impact on imaging. Our approach integrates generative artificial intelligence with physics-informed common-image gathers, reducing reliance on accurate initial velocity models. Considered case studies demonstrate its efficacy producing realizations of migration-velocity models conditioned by the data. These models are used to quantify amplitude and positioning effects during subsequent imaging.

Funder

ML4SEISMIC

Georgia Research Alliance

Publisher

Society of Exploration Geophysicists

Link

https://library.seg.org/doi/pdf/10.1190/geo2023-0744.1

Reference45 articles.

1. Baldassari, L., A. Siahkoohi, J. Garnier, K. Solna, and M. V. de Hoop, 2024, Conditional score-based diffusion models for Bayesian inference in infinite dimensions: Advances in Neural Information Processing Systems.

2. Deng, C., S. Feng, H. Wang, X. Zhang, P. Jin, Y. Feng, Q. Zeng, Y. Chen, and Y. Lin, 2022, OpenFWI: Large-scale multi-structural benchmark datasets for full waveform inversion: Advances in Neural Information Processing Systems, 6007–6020.

3. Time‐migration velocity analysis by velocity continuation

4. Gahlot, A. P., H. T. Erdinc, R. Orozco, Z. Yin, and F. J. Herrmann, 2023, Inference of CO2 flow patterns — A feasibility study: NeurIPS 2023 Workshop — Tackling Climate Change with Machine Learning.

5. Deep learning for velocity model building with common-image gather volumes

Cited by 3 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献

1. Geophysics Bright Spots;The Leading Edge;2024-09

2. Controllable Seismic Velocity Synthesis Using Generative Diffusion Models;Journal of Geophysical Research: Machine Learning and Computation;2024-08-08

3. Time-lapse full-waveform permeability inversion: A feasibility study;The Leading Edge;2024-08