Urip Nurwijayanto Prabowo, Sudarmaji Saroji, Sismanto Sismanto
{"title":"Geophysical-guided Wasserstein cycle-consistent generative adversarial networks for seismic impedance inversion","authors":"Urip Nurwijayanto Prabowo, Sudarmaji Saroji, Sismanto Sismanto","doi":"10.1007/s11600-025-01536-2","DOIUrl":null,"url":null,"abstract":"<div><p>Deep learning has shown great ability to solve the nonlinear inversion problem in geophysical fields. Insufficient-labeled data and a lack of geophysical constraints become the main challenges in training the networks. In seismic impedance inversion, combined semisupervised learning and generative adversarial networks (GANs) named cycle-consistent GAN (cyc-GAN) are proven to achieve better inversion accuracy with insufficient labeled data. The next improvement of cyc-GAN is Geo-cyc-GAN, which imposes the convolutional model as a geophysical constraint. This improvement can speed up the training process and achieve better accuracy. However, like most GAN algorithms, the cyc-GAN and Geo-cyc-GAN suffer from training instability. Therefore, we proposed geophysical-guided Wasserstein cycle-consistent generative adversarial networks (Geo-cyc-WGANs) to overcome the training instability of GAN and increase its accuracy. Geo-cyc-WGAN uses Wasserstein distance as a loss function instead of cross-entropy to improve the training stability. The experiment results of synthetic data using small labeled traces show that Geo-cyc-WGAN achieves the highest accuracy, better lateral continuity, and a more stable training process than another geophysical guide-based method. The experiment results of real data also show that Geo-cyc-WGAN can obtain better accurate impedance results than other methods.</p></div>","PeriodicalId":6988,"journal":{"name":"Acta Geophysica","volume":"73 3","pages":"2621 - 2634"},"PeriodicalIF":2.3000,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Acta Geophysica","FirstCategoryId":"89","ListUrlMain":"https://link.springer.com/article/10.1007/s11600-025-01536-2","RegionNum":4,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
Abstract
Deep learning has shown great ability to solve the nonlinear inversion problem in geophysical fields. Insufficient-labeled data and a lack of geophysical constraints become the main challenges in training the networks. In seismic impedance inversion, combined semisupervised learning and generative adversarial networks (GANs) named cycle-consistent GAN (cyc-GAN) are proven to achieve better inversion accuracy with insufficient labeled data. The next improvement of cyc-GAN is Geo-cyc-GAN, which imposes the convolutional model as a geophysical constraint. This improvement can speed up the training process and achieve better accuracy. However, like most GAN algorithms, the cyc-GAN and Geo-cyc-GAN suffer from training instability. Therefore, we proposed geophysical-guided Wasserstein cycle-consistent generative adversarial networks (Geo-cyc-WGANs) to overcome the training instability of GAN and increase its accuracy. Geo-cyc-WGAN uses Wasserstein distance as a loss function instead of cross-entropy to improve the training stability. The experiment results of synthetic data using small labeled traces show that Geo-cyc-WGAN achieves the highest accuracy, better lateral continuity, and a more stable training process than another geophysical guide-based method. The experiment results of real data also show that Geo-cyc-WGAN can obtain better accurate impedance results than other methods.
期刊介绍:
Acta Geophysica is open to all kinds of manuscripts including research and review articles, short communications, comments to published papers, letters to the Editor as well as book reviews. Some of the issues are fully devoted to particular topics; we do encourage proposals for such topical issues. We accept submissions from scientists world-wide, offering high scientific and editorial standard and comprehensive treatment of the discussed topics.