1887

Abstract

Summary

Conventional fault interpretation workflows in reflection seismic data is not only time-consuming but also subject to significant human-bias, which is difficult to quantify reliably. In this study, we apply 3D Deep Learning (DL) networks trained on synthetic 3D seismic datasets, to a seismic survey from the Polhem Subplatform, SW Barents Sea for automatic generation of probabilistic fault volumes. The detailed extraction of fault segments from the prediction of DL algorithms enables a multiscale characterization of the seismic fault zone architecture in 3D. These fault zones are affected by the presence of unconformities. Our results indicate that the maximum segment lengths of the faults occur near their upper tips and progressively decrease towards the lower tips. Fault zone widths, measured on E–W-oriented scanlines-trending orthogonal to the dominant fault-strike at various depth intervals, generally range between 10–20m. It increases where fault segments either link laterally/vertically or interact with antithetic fault sets with similar strike as that of the dominant westward-dipping fault set. Fault zone widths and throw are greater towards the lower tips of faults. Thus, the DL-based approach utilized in this study enables the extraction of reliable, quantitative insights into the seismic fault zone architecture, while significantly reducing interpretation-based uncertainty.

© EAGE Publications BV
Loading

Article metrics loading...

/content/papers/10.3997/2214-4609.202532025
2025-09-14
2026-02-15

  • From This Site

    /content/papers/10.3997/2214-4609.202532025
    dcterms_title,dcterms_subject,pub_keyword
    -contentType:Journal -contentType:Contributor -contentType:Concept -contentType:Institution
    10
    5
Loading full text...

Full text loading...

References

  1. Alaei, B., & Torabi, A. [2017]. Seismic imaging of fault damaged zone and its scaling relation with displacement. Interpretation, 5(4), SP83–SP93.
     [Google Scholar]
  2. Alaei, B., & Torabi, A. [2024]. Fault asperity and roughness, insight from faults in 3D reflection seismic data. Marine and Petroleum Geology, 170, 107145.
     [Google Scholar]
  3. An, Y., Du, H., Ma, S., Niu, Y., Liu, D., Wang, J., Du, Y., Childs, C., Walsh, J. & Dong, R. [2023]. Current state and future directions for deep learning based automatic seismic fault interpretation: A systematic review. Earth-Science Reviews, 243, 104509.
     [Google Scholar]
  4. Bond, C. E. [2015]. Uncertainty in structural interpretation: Lessons to be learnt. Journal of Structural Geology, 74, 185–200.
     [Google Scholar]
  5. Bönke, W., Alaei, B., Torabi, A., & Oikonomou, D. [2024]. Data augmentation for 3D seismic fault interpretation using deep learning. Marine and Petroleum Geology, 162, 106706.
     [Google Scholar]
  6. Brito, L. S. B., Alaei, B., Torabi, A., Leopoldino-Oliveira, K. M., Lino Vasconcelos, D., Bezerra, F. H. R., & Nogueira, F. C. C. [2023]. Automatic 3D fault detection and characterization—A comparison between seismic attribute methods and deep learning. Interpretation, 11(4), T793–T808.
     [Google Scholar]
  7. Dyer, L., & Manral, S. [2022]. Machine learning assisted seismic interpretation: a case study of the Loppa high area, Barents Sea. First Break, 40(11), 33–39.
     [Google Scholar]
  8. Gabrielsen, R. H., Faleide, J. I., Leever, K. A., & Grunnaleite, I. [2011]. Strike-slip related inversion-tectonics of the southwestern Barents Sea (Norwegian Shelf) in a plate tectonic perspective. In Geophys. Res. Abstr (Vol. 13).
     [Google Scholar]
  9. Indrevær, K., Gabrielsen, R. H., & Faleide, J. I. [2017]. Early Cretaceous synrift uplift and tectonic inversion in the Loppa High area, southwestern Barents Sea, Norwegian shelf. Journal of the Geological Society, 174(2), 242–254.
     [Google Scholar]
  10. Oikonomou, D., Larsen, E., Alaei, B., Stefos, G., & Purves, S. [2019, June]. EarthNET a native cloud web based solution for next generation subsurface workflows. In 81st EAGE Conference and Exhibition 2019 Workshop Programme (Vol. 2019, No. 1, pp. 1–4). European Association of Geoscientists & Engineers.
     [Google Scholar]
  11. Oliveira, L. S. B., Nogueira, F. C. C., Vasconcelos, D. L., Torabi, A., Alaei, B., Balsamo, F., … & Souza, J. A. B. [2024]. Seismic and outcrop-based 3D characterization of fault damage zones in sandstones, Rio do Peixe Basin, Brazil. Journal of Structural Geology, 189, 105276.
     [Google Scholar]
  12. Ronneberger, O., Fischer, P., & Brox, T. [2015]. U-net: Convolutional networks for biomedical image segmentation. In Medical image computing and computer-assisted intervention–MICCAI 2015: 18th international conference, Munich, Germany, October 5–9, 2015, proceedings, part III 18 (pp. 234–241). Springer international publishing.
     [Google Scholar]
  13. Solum, J., Onyeagoro, K., & Boles, A. (2022, September). Improving fault seal analysis through innovative fault interpretation. In Sixth International Conference on Fault and Top Seals (Vol. 2022, No. 1, pp. 1–5). European Association of Geoscientists & Engineers.
     [Google Scholar]
  14. Torabi, A., & Berg, S. S. [2011]. Scaling of fault attributes: A review. Marine and Petroleum geology, 28(8), 1444–1460.
     [Google Scholar]
  15. Torabi, A., Alaei, B., & Libak, A. [2019]. Normal fault 3D geometry and displacement revisited: Insights from faults in the Norwegian Barents Sea. Marine and Petroleum Geology, 99, 135–155.
     [Google Scholar]
  16. Torabi, A., Balsamo, F., Nogueira, F. C., Vasconcelos, D. L., Silva, A. C., Bezerra, F. H., & Souza, J. A. [2021]. Variation of thickness, internal structure and petrophysical properties in a deformation band fault zone in siliciclastic rocks. Marine and Petroleum Geology, 133, 105297.
     [Google Scholar]
  17. Torabi, A., Rudnicki, J., Alaei, B., & Buscarnera, G. [2023]. Envisioning faults beyond the framework of fracture mechanics. Earth-Science Reviews, 238, 104358.
     [Google Scholar]
/content/papers/10.3997/2214-4609.202532025
Loading
A New Approach to Multi-Scale Characterization of the 3D Seismic Fault Zone Architecture using Deep Learning
Conference Proceedings 2025, 1 (2025); https://doi.org/10.3997/2214-4609.202532025
/content/papers/10.3997/2214-4609.202532025
/content/papers/10.3997/2214-4609.202532025
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