1887

Abstract

Summary

Seismic interpolation is a common step in data processing, to infill missing traces, regularize acquisition grids, or in 4D seismic applications. In this study we use the Generative Adversarial Network (GAN) Pix2Pix together with an iterative workflow to carry out interpolation of seismic data using different domains to train and to do the prediction. Our iterative method trains and makes predictions using different gather domains, allowing to use all the survey to train and generate predictions without overfitting. We illustrate the workflow using synthetic data modeled after Ocean Bottom Node (OBN) surveys, which comprise densely populated receiver gathers and sparsely populated shot gathers. The workflow may be used to interpolate missing traces or even complete the geometry of a monitor acquisition to make it match the baseline. For larger infill gaps, the iterative GAN interpolation does not add artifacts like when using conventional methods.

© EAGE Publications BV
Loading

Article metrics loading...

/content/papers/10.3997/2214-4609.202310732
2023-06-05
2026-03-10

  • From This Site

    /content/papers/10.3997/2214-4609.202310732
    dcterms_title,dcterms_subject,pub_keyword
    -contentType:Journal -contentType:Contributor -contentType:Concept -contentType:Institution
    10
    5
Loading full text...

Full text loading...

References

  1. Chang, D., Yang, W., Yong, X., and Li, H. [2018]. Generative Adversarial Networks for Seismic Data Interpolation. SEG 2018 Workshop: SEG Maximizing Asset Value Through Artificial Intelligence and Machine Learning, Beijing, China, 17–19 September 2018, 40–43.
     [Google Scholar]
  2. Fang, W., Fu, L., Zhang, M., and Li, Z. [2021]. Seismic data interpolation based on U-net with texture loss. GEOPHYSICS, 86(1), V41–V54.
     [Google Scholar]
  3. Fomel, S. [2001]. Applications of Plane-Wave Destructor Filters. Geophysics, 67.
     [Google Scholar]
  4. Goodfellow, I. J., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., and Bengio, Y. [2014, June 10]. Generative Adversarial Networks.
     [Google Scholar]
  5. Isola, P., Zhu, J.-Y., Zhou, T., and Efros, A. A. [2018, November 26]. Image-to-Image Translation with Conditional Adversarial Networks.
     [Google Scholar]
  6. Kaur, H., Pham, N., and Fomel, S. [2021]. Seismic data interpolation using deep learning with generative adversarial networks. Geophysical Prospecting, 69(2), 307–326.
     [Google Scholar]
  7. Kumar, R., Amin, Y. I. K., Sonika, S., Vassallo, M., and Allouche, N. E. [2020]. Dense ocean-bottom node interpolation using priors derived from reciprocity. In SEG Technical Program Expanded Abstracts. SEG Technopertoical Program Expanded Abstracts 2020 (pp. 3144–3148).
     [Google Scholar]
  8. Mojica, O. F., and Maciel, J. S. [2020]. Seismic modeling from scratch using Devito: A demonstration with a typical Brazilian pre-salt model. In SEG Technical Program Expanded Abstracts. SEG Technical Program Expanded Abstracts 2020 (pp. 2714–2718).
     [Google Scholar]
  9. Operto, S., Miniussi, A., Brossier, R., Combe, L., Métivier, L., Monteiller, V., Ribodetti, A., and Virieux, J. [2015]. Efficient 3-D frequency-domain mono-parameter full-waveform inversion of ocean-bottom cable data: application to Valhall in the visco-acoustic vertical transverse isotropic approximation. Geophysical Journal International, 202(2), 1362–1391.
     [Google Scholar]
  10. Spitz, S. [1991]. Seismic trace interpolation in the F-X domain. GEOPHYSICS, 56(6), 785–794.
     [Google Scholar]
  11. Thorbecke, J. W., and Draganov, D. [2011]. Finite-difference modeling experiments for seismic interferometry. GEOPHYSICS, 76(6), H1–H18.
     [Google Scholar]
/content/papers/10.3997/2214-4609.202310732
Loading
Seismic data interpolation with an iterative workflow and generative adversarial networks
Conference Proceedings 2023, 1 (2023); https://doi.org/10.3997/2214-4609.202310732
/content/papers/10.3997/2214-4609.202310732
/content/papers/10.3997/2214-4609.202310732
Loading

Data & Media loading...

Most Cited This Month Most Cited RSS feed

This is a required field
Please enter a valid email address
Approval was a Success
Invalid data
An Error Occurred
Approval was partially successful, following selected items could not be processed due to error