CoChat
Sign Up
Cited by 10Seismic Imaging and Inversion TechniquesSeismic Waves and AnalysisModel Reduction and Neural Networks

The DOI matches its Crossref record; 4 of the 4 references it cites were found in a registry or an index.

An empirical study of large-scale data-driven full waveform inversion

Open access
Jin, Peng, Feng, Yinan, Feng, Shihang, Wang, Hanchen, Chen, Yinpeng, Consolvo, Benjamin, Liu, Zicheng, Lin, Youzuo·2024·Scientific Reports
DOI 10.1038/s41598-024-68573-7PMC PMC11358280

Published version of a preprint

Open this paper in CoChat — free accountOpen PDF

Abstract

This paper investigates the impact of big data on deep learning models to help solve the full waveform inversion (FWI) problem. While it is well known that big data can boost the performance of deep learning models in many tasks, its effectiveness has not been validated for FWI. To address this gap, we present an empirical study that investigates how deep learning models in FWI behave when trained on OPENFWI, a collection of large-scale, multi-structural, synthetic datasets published recently. In particular, we train and evaluate the FWI models on a combination of 10 2D subsets in OPENFWI that contain 470 K pairs of seismic data and velocity maps in total. Our experiments demonstrate that training on the combined dataset yields an average improvement of 13.03% in MAE, 7.19% in MSE and 1.87% in SSIM compared to each split dataset, and an average improvement of 28.60%, 21.55% and 8.22% in the leave-one-out generalization test. We further demonstrate that model capacity needs to scale in accordance with data size for optimal improvement, where our largest model yields an average improvement of 20.06%, 13.39% and 0.72% compared to the smallest one.

Overview

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1038/s41598-024-68573-7

Cites

4 of 4 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Flagged first, then by citations

Research works printed but not linked: 40

  1. Sun, C., Shrivastava, A., Singh, S. & Gupta, A. Revisiting unreasonable effectiveness of data in deep learning era. In Proc. IEEE International Conference on Computer Vision 843–852 (2017). · DOI · Paper page
  2. Kolesnikov, A. et al. Big transfer (bit): General visual representation learning. In European Conference on Computer Vision 491–507 (Springer, 2020). · DOI · Paper page
  3. Schuhmann, C. et al. Laion-5b: An open large-scale dataset for training next generation image-text models. In Thirty-Sixth Conference on Neural Information Processing Systems Datasets and Benchmarks Track.
  4. Tarantola, A. Inversion of seismic reflection data in the acoustic approximation. Geophysics 49, 1259–1266 (1984). · DOI
  5. Pratt, R. G., Shin, C. & Hick, G. Gauss-newton and full newton methods in frequency-space seismic waveform inversion. Geophys. J. Int. 133, 341–362 (1998). · DOI
  6. Plessix, R.-E. A review of the adjoint-state method for computing the gradient of a functional with geophysical applications. Geophys. J. Int. 167, 495–503 (2006). · DOI
  7. Virieux, J. & Operto, S. An overview of full-waveform inversion in exploration geophysics. Geophysics 74, 1–26 (2009). · DOI
  8. Fichtner, A. Full Seismic Waveform Modelling and Inversion (Springer, 2010).
  9. Zhang, Z., Huang, L. & Lin, Y. A wave-energy-based precondition approach to full-waveform inversion in the time domain. In SEG Technical Program Expanded Abstracts 2012 1–5 (Society of Exploration Geophysicists, 2012). · DOI
  10. Ma, Y., Hale, D., Gong, B. & Meng, Z. Image-guided sparse-model full waveform inversion. Geophysics 77, R189–R198 (2012). · DOI
  11. Zhang, Z. & Huang, L. Double-difference elastic-waveform inversion with prior information for time-lapse monitoring. Geophysics 78, R259–R273 (2013). · DOI
  12. Feng, S. & Schuster, G. T. Transmission+ reflection anisotropic wave-equation traveltime and waveform inversion. Geophys. Prospect. 67, 423–442 (2019). · DOI
  13. Feng, S., Fu, L., Feng, Z. & Schuster, G. T. Multiscale phase inversion for vertical transverse isotropic media. Geophys. Prospect. 69, 1634–1649 (2021). · DOI
  14. Lin, Y. & Huang, L. Acoustic-and elastic-waveform inversion using a modified total-variation regularization scheme. Geophys. J. Int. 200, 489–502 (2014). · DOI
  15. Lin, Y. & Huang, L. Quantifying subsurface geophysical properties changes using double-difference seismic-waveform inversion with a modified Total-Variation regularization scheme. Geophys. J. Int. 203, 2125–2149 (2015). · DOI
  16. Hu, W., Abubakar, A. & Habashy, T. M. Simultaneous multifrequency inversion of full-waveform seismic data. Geophysics 74, R1–R14 (2009). · DOI
  17. Guitton, A. Blocky regularization schemes for full-waveform inversion. Geophys. Prospect. 60, 870–884 (2012). · DOI
  18. Chen, Y. et al. Multiscale reflection phase inversion with migration deconvolution. Geophysics 85, R55–R73 (2020). · DOI
  19. Wang, W. & Ma, J. Velocity model building in a crosswell acquisition geometry with image-trained artificial neural networks. Geophysics 85, U31–U46 (2020). · DOI
  20. Liu, B. et al. Deep-learning seismic full-waveform inversion for realistic structural modelsdl seismic fwi. Geophysics 86, R31–R44 (2021). · DOI
  21. Araya-Polo, M., Jennings, J., Adler, A. & Dahlke, T. Deep-learning tomography. Lead. Edge 37, 58–66 (2018). · DOI · Paper page
  22. Yang, F. & Ma, J. Deep-learning inversion: A next-generation seismic velocity model building method. Geophysics 84, R583–R599 (2019). · DOI
  23. Ren, Y., Nie, L., Yang, S., Jiang, P. & Chen, Y. Building complex seismic velocity models for deep learning inversion. IEEE Access 9, 63767–63778 (2021). · DOI
  24. Geng, Z. et al. Deep learning for velocity model building with common-image gather volumes. Geophys. J. Int. 228, 1054–1070 (2022). · DOI
  25. Lin, Y., Theiler, J. & Wohlberg, B. Physics-guided data-driven seismic inversion: Recent progress and future opportunities in full-waveform inversion. IEEE Signal Process. Mag. 40, 115–133 (2023). · DOI
  26. Wu, Y. & Lin, Y. InversionNet: An efficient and accurate data-driven full waveform inversion. IEEE Trans. Comput. Imaging 6, 419–433 (2019). · DOI
  27. Zhang, Z. & Lin, Y. Data-driven seismic waveform inversion: A study on the robustness and generalization. IEEE Trans. Geosci. Remote Sens. 58, 6900–6913 (2020). · DOI
  28. Araya-Polo, M. et al. Automated fault detection without seismic processing. Lead. Edge 36, 208–214 (2017). · DOI
  29. Deng, C. et al. Openfwi: Large-scale multi-structural benchmark datasets for full waveform inversion. Adv. Neural. Inf. Process. Syst. 35, 6007–6020 (2022).
  30. Yang, Y., Engquist, B., Sun, J. & Hamfeldt, B. F. Application of optimal transport and the quadratic Wasserstein metric to full-waveform inversion. Geophysics 83, R43–R62 (2018). · DOI
  31. Bonneel, N., Rabin, J., Peyré, G. & Pfister, H. Sliced and radon wasserstein barycenters of measures. J. Math. Imaging Vis. 51, 22–45 (2015). · DOI
  32. Brougois, A. et al. Marmousi, model and data. In EAEG Workshop-Practical Aspects of Seismic Data Inversion 108 (European Association of Geoscientists & Engineers, 1990). · DOI
  33. Martin, G. S., Wiley, R. & Marfurt, K. J. Marmousi2: An elastic upgrade for marmousi. Lead. Edge 25, 156–166 (2006). · DOI
  34. Aminzadeh, F., Burkhard, N., Long, J., Kunz, T. & Duclos, P. Three dimensional seg/eaeg models—An update. Lead. Edge 15, 131–134 (1996). · DOI
  35. Aminzadeh, F., Weimer, P. & Davis, T. 3-d salt and overthrust seismic models. Stud. Geol. 42, 247–256 (1996).
  36. Feng, S., Lin, Y. & Wohlberg, B. Multiscale data-driven seismic full-waveform inversion with field data study. IEEE Trans. Geosci. Remote Sens. 60, 1–14. https://doi.org/10.1109/TGRS.2021.3114101 (2021). · DOI
  37. Jin, P. et al. Unsupervised learning of full-waveform inversion: Connecting CNN and partial differential equation in a loop. In Proc. Tenth International Conference on Learning Representations (ICLR) (2022).
  38. Feng, Y. et al. An intriguing property of geophysics inversion. In Proc. Thirty-ninth International Conference on Machine Learning (ICML) (2022).
  39. Zhu, M., Feng, S., Lin, Y. & Lu, L. Fourier-deeponet: Fourier-enhanced deep operator networks for full waveform inversion with improved accuracy, generalizability, and robustness. Comput. Methods Appl. Mech. Eng. 416, 116300 (2023). · DOI
  40. Vaswani, A. et al. Attention is all you need. Adv. Neural Inf. Process. Syst. 30, 1 (2017).

Metadata

Authors
Jin, P., Feng, Y., Feng, S., Wang, H., Chen, Y., Consolvo, B., Liu, Z., & Lin, Y.
Affiliations
  • Pennsylvania State University (US)
  • Los Alamos National Laboratory (US)
  • Google (United States) (US)
  • Intel (United States) (US)
  • Microsoft (United States) (US)
  • University of North Carolina at Chapel Hill (US)
Corresponding author
  • Jin, Peng
  • Lin, Youzuo
ORCID
Venue
Scientific Reports
Publisher
Springer Science and Business Media LLC
Published
2024-08-28
Volume
14
Issue
1
Pages
20034-20034
ISSN
2045-2322 (ISSN-L)
DOI
10.1038/s41598-024-68573-7
PMC
PMC11358280
OpenAlex
W4401938289
Cited by
10
References
4
Citations by year
2026: 5 · 2025: 5
FWCI
2.58
Type
journal article
Language
en
Open access
Licence
Locations
  • Scientific Reports (publishedVersion, cc-by-nc-nd)
  • Research Square (acceptedVersion, cc-by)
  • PubMed Central (publishedVersion, cc-by-nc-nd)
  • PubMed (publishedVersion)
  • DOAJ (DOAJ: Directory of Open Access Journals) (publishedVersion)
  • arXiv (Cornell University) (submittedVersion, cc-by)
  • OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information) (submittedVersion)
  • arXiv (Cornell University) (cc-by)
Funders
  • U.S. Department of Energy
  • University of North Carolina at Chapel Hill
Topics
  • Physical Sciences › Earth and Planetary Sciences › Geophysics › Seismic Imaging and Inversion Techniques
  • Physical Sciences › Earth and Planetary Sciences › Geophysics › Seismic Waves and Analysis
  • Physical Sciences › Physics and Astronomy › Statistical and Nonlinear Physics › Model Reduction and Neural Networks
Keywords
full waveform inversion, big data, deep learning, synthetic seismic data, model capacity, dataset size, velocity model building, seismic imaging

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review