An unsupervised physics-constrained velocity inversion method based on spectral normalization adversarial learning

Clicks: 8
ID: 331663
2026
Free PDF
Article Quality & Performance Metrics
Overall Quality
Not rated
Combines reader engagement with the AI quality analysis. This article has not been analysed, so there is no overall score — reader engagement is measured and shown alongside.
AI Quality Assessment
Not analyzed
Readership in this journal
Emerging

Ranked #321 of 337 articles by views in geophysical journal international

Most read Least read

Bar heights use a square-root scale. Only the 120 most-read articles are drawn; the journal has 337 in total.

Mint this article as an NFT
Not yet minted

Create a permanent, verifiable on-chain record of this article on the Scimatic Network. The NFT is held in your Journament account, and you can withdraw it to your own wallet at any time.

5 SUSD one-off · no wallet required
Sign in to mint
Abstract
Summary Full waveform inversion (FWI) has significant potential to reconstruct the subsurface structure at high resolution, but it is a nonlinear and ill-posed problem. Traditional physics-based FWI methods that employ gradient-based optimization algorithms to minimize the discrepancy between observed and synthetic data face several challenges. The aforementioned methods are susceptible to becoming trapped in local minima as a result of cycle-skipping problems and require substantial computational resources, particularly with the increasing size and required resolution of seismic datasets. Nowadays many deep-learning methods are proposed to solve the above challenges. FWIGAN, a recently proposed unsupervised seismic velocity inversion method based on the Wasserstein generative adversarial network with gradient penalty (WGAN-GP), has demonstrated certain success in overcoming these challenges. However, FWIGAN enforces the Lipschitz constraint on the critic through a gradient penalty evaluated at dynamically sampled interpolation points between the observed and synthetic data. This strategy introduces additional computational and hyperparameter tuning costs. Motivated by these limitations, we introduce the spectral normalization into the FWIGAN framework, directly constraining the spectral norm of each network layer to control the Lipschitz behavior of the critic. It can enhance the stability of network training. The proposed method mitigates the dependence on having large labeled data and the pretraining of the network. The new scheme is applied to the Marmousi and Sigsbee models to verify its robust performance. The experimental results clearly indicate that our method outperforms common methods in terms of inversion accuracy.
Reference Key
openalex_W7220854779 Use this key to autocite in the manuscript while using SciMatic Manuscript Manager or Thesis Manager
Authors Cong Wang, Xingguo Huang, Stewart Greenhalgh, S Mostafa Mousavi, Yunfeng Chen, Yue Li
Are you one of these authors? Claim your profile
Journal geophysical journal international
Year 2026
DOI
10.1093/gji/ggag418
URL
https://doi.org/10.1093/gji/ggag418
Keywords Keywords not found

Citations

No citations found. To add a citation, contact the admin at info@scimatic.org

Comments

No comments yet. Be the first to comment on this article.