1887

Abstract

Summary

Fault interpretation is sometimes considered biased and requires years of experience and expertise. It is crucial to delineate faults accurately to gain a comprehensive understanding of the complete petroleum system. Many methods have proven useful in interpreting faults based on seismic data, with various attributes providing numerous fault extraction methodologies. In this study, we apply a 3D Convolutional Neural Network (CNN) as an alternative approach for fault extraction using full stack and near stack seismic data. CNNs excel in image segmentation tasks, contributing significantly to the delineation of fault discontinuities and in this study has yielded promising results, with the identification of smaller faults that were previously undetectable. Near stack data provides higher resolution and clearer imaging of shallow subsurface structures, enabling the CNN model to detect faults with greater precision. This approach is shown to be vital as it helps understand both uncertainties and certainties that are crucial for reservoir characterization.

© EAGE Publications BV
Loading

Article metrics loading...

/content/papers/10.3997/2214-4609.202477101
2024-11-20
2026-02-15

  • From This Site

    /content/papers/10.3997/2214-4609.202477101
    dcterms_title,dcterms_subject,pub_keyword
    -contentType:Journal -contentType:Contributor -contentType:Concept -contentType:Institution
    10
    5
Loading full text...

Full text loading...

References

  1. Marfurt, K. J., R. L.Kirlin, S. L.Farmer, and M. S.Bahorich, 1998, 3-D seismic attributes using a semblance-based coherency algorithm: Geophysics, 63, 1150–1165, doi: 10.1190/1.14444.5.
     https://doi.org/10.1190/1.14444.5 [Google Scholar]
  2. Marfurt, K. J., V.Sudhaker, A.Gersztenkorn, K. D.Crawford, and S. E.Nissen, 1999, Coherency calculations in the presence of structural dip: Geophysics, 64, 104–111, doi: 10.1190/1.14445.8.
     https://doi.org/10.1190/1.14445.8 [Google Scholar]
  3. Randen, T., S. I.Pedersen, and L.Sønneland, 2001, Automatic extraction of fault surfaces from three dimensional seismic data: 81st Annual International Meeting, SEG, Expanded Abstracts, 551–554, doi: 10.1190/1.18166.5.
     https://doi.org/10.1190/1.18166.5 [Google Scholar]
  4. Wu, Xinming & Liang, Luming & Shi, Yunzhi & Fomel, Sergey. 2019. FaultSeg3D: Using synthetic data sets to train an end-to-end convolutional neural network for 3D seismic fault segmentation. Geophysics. 84. IM35–IM45. 10.1190/geo2018‑0646.1.
     https://doi.org/10.1190/geo2018-0646.1 [Google Scholar]
  5. Wu, Xinming & Hale, Dave. 2016. 3D seismic image processing for faults. Geophysics. 81. IM1–IM11. 10.1190/geo2015‑0380.1.
     https://doi.org/10.1190/geo2015-0380.1 [Google Scholar]
  6. Cunha, Augusto & Pochet, Axelle & Lopes, Helio & Gattass, Marcelo. (2019). Seismic fault detection in real data using transfer learning from a convolutional neural network pre-trained with synthetic seismic data. Computers & Geosciences. 135. 104344. 10.1016/j.cageo.2019.104344.
     https://doi.org/10.1016/j.cageo.2019.104344 [Google Scholar]
  7. Faleide, Thea & Braathen, Alvar & Lecomte, Isabelle & Mulrooney, Mark & Midtkandal, Ivar & Bugge, Aina & Planke, Sverre. (2021). Impacts of seismic resolution on fault interpretation: Insights from seismic modelling. Tectonophysics. 816. 229008. 10.1016/j.tecto.2021.229008.
     https://doi.org/10.1016/j.tecto.2021.229008 [Google Scholar]
/content/papers/10.3997/2214-4609.202477101
Loading
3D Convolutional Neural Network for Fault Extraction Based on Angle Seismic Stack
Conference Proceedings 2024, 1 (2024); https://doi.org/10.3997/2214-4609.202477101
/content/papers/10.3997/2214-4609.202477101
/content/papers/10.3997/2214-4609.202477101
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