1887
Volume 73, Issue 2
  • E-ISSN: 1365-2478

Abstract

Abstract

Fault detection is a crucial step in seismotectonic interpretation and oil–gas exploration. In recent years, deep learning has gradually proven to be an effective approach for detecting faults. Due to complex geological structures and seismic noise, detection results of such approaches remain unsatisfactory. In this study, we propose a hybrid network (NRA‐SANet) that integrates a self‐attention mechanism into a nested residual attention network for a three‐dimensional seismic fault segmentation task. In NRA‐SANet, the nested residual coding structure is designed to fuse multi‐scale fault features, which can fully mine fine‐grained fault information. The two‐head self‐attention decoding structure is designed to construct long‐distance fault dependencies from different feature representation subspaces, which can enhance the understanding of the model regarding the global fault distribution. In order to suppress the interference of seismic noise, we propose a fault‐attention module and embed it into the model. It utilizes the weighted and the separate‐and‐reconstruct channel strategy to improve the model sensitivity to fault areas. Experiments demonstrate that NRA‐SANet exhibits strong noise robustness, while it can also detect more continuous and more small‐scale faults than other approaches on field seismic data. This study provides a new idea to promote the development of seismic interpretation.

© 2025 European Association of Geoscientists & Engineers. © 2024 European Association of Geoscientists & Engineers.
Loading

Article metrics loading...

/content/journals/10.1111/1365-2478.13655
2025-01-26
2025-11-14

  • From This Site

    /content/journals/10.1111/1365-2478.13655
    dcterms_title,dcterms_subject,pub_keyword
    -contentType:Journal -contentType:Contributor -contentType:Concept -contentType:Institution
    10
    5
Loading full text...

Full text loading...

References

  1. Alohali, R., Al‐Zubaidi, F.A., Kranendonk, M.J.V. & Clark, S.R. (2022) Automated fault detection in the Arabian Basin. Geophysics, 87, IM101–IM109.
     [Google Scholar]
  2. Aqrawi, A.A. (2014) Adaptive Sobel based edge detection for enhanced fault segmentation. Paper IPTC‐17543‐MS. Paper presented at the International Petroleum Technology Conference, Doha, Qatar, January 2014.
  3. Bahorich, M.S. & Farmer, S.L. (1995) 3‐D seismic discontinuity for faults and stratigraphic features: the coherence cube. In the SEG technical program expanded abstracts, 14. Houston, TX: Society of Exploration Geophysicists, pp. 1053–1058.
  4. Chen, G. & Lyu, S. (2015) Application of RGB frequency division technology in the fault identification of fault‐block reservoir. Complex Hydrocarbon Reservoirs, 8, 29–32.
     [Google Scholar]
  5. Chopra, S., Kumar, R. & Marfurt, K.J. (2014) Seismic discontinuity attributes and Sobel filtering. In the SEG technical program expanded abstracts 2014. Houston, TX: Society of Exploration Geophysicists, pp. 1624–1628.
  6. Cohen, I., Coult, N. & Vassiliou, A.A. (2006) Detection and extraction of fault surfaces in 3‐D seismic data. In the SEG technical program expanded abstracts 2006. Houston, TX: Society of Exploration Geophysicists, pp. 21–27.
  7. Crampin, S. (1984) Effective anisotropic elastic constants for wave propagation through cracked solids. Geophysical Journal International, 76, 135–145.
     [Google Scholar]
  8. Dou, Y., Li, K., Dong, M. & Xiao, Y. (2024) FaultSSL: seismic fault detection via semi‐supervised learning. Geophysics, 89, 79–91.
     [Google Scholar]
  9. Dou, Y., Li, K., Zhu, J., Li, T., Tan, S. & Huang, Z. (2022) MD loss: efficient training of 3‐D seismic fault segmentation network under sparse labels by weakening anomaly annotation. IEEE Transactions on Geoscience and Remote Sensing, 60, 1–14.
     [Google Scholar]
  10. Dou, Y., Li, K., Zhu, J., Li, X. & Xi, Y. (2021) Attention‐based 3‐D seismic fault segmentation training by a few 2‐D slice labels. IEEE Transactions on Geoscience and Remote Sensing, 60, 1–15.
     [Google Scholar]
  11. Fu, J., Liu, J., Jiang, J., Li, Y., Bao, Y. & Lu, H. (2021) Scene segmentation with dual relation‐aware attention network. IEEE Transactions on Neural Networks and Learning Systems, 32(6), 2547–2560.
     [Google Scholar]
  12. Gao, K., Huang, L. & Zheng, Y. (2022) Fault detection on seismic structural images using a nested residual U‐Net. IEEE Transactions on Geoscience and Remote Sensing, 60, 1–15.
     [Google Scholar]
  13. Gao, K., Huang, L., Zheng, Y., Lin, R., Hu, H. & Cladouhos, T.T. (2022) Automatic fault detection on seismic images using a multiscale attention convolutional neural network. Geophysics, 87, N13–N29.
     [Google Scholar]
  14. Gersztenkorn, A. & Marfurt, K.J. (1999a) Eigenstructure‐based coherence computations as an aid to 3‐D structural and stratigraphic mapping. Geophysics, 64, 1468–1479.
     [Google Scholar]
  15. Gersztenkorn, A. & Marfurt, K.J. (1999b) Eigenstructure‐based coherence computations as an aid to 3‐D structural and stratigraphic mapping. Geophysicists, 64, 1468–1479.
     [Google Scholar]
  16. Han, T., Ding, R., Zhao, S., Ma, Y., Su, C., Zhang, Y., Li, J. & Zhao, L. (2023) Algorithm for intelligent recognition low‐grade seismic faults using codec target edges. IEEE Transactions on Geoscience and Remote Sensing, 61, 1–12.
     [Google Scholar]
  17. He, K., Zhang, X., Ren, S. & Sun, J. (2016) Deep residual learning for image recognition. In the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Piscataway, NJ: IEEE, pp. 770–778.
  18. Hu, J., Shen, L. & Sun, G. (2018) Squeeze‐and‐excitation networks. In the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, pp. 7132–7141.
  19. Hung, A. L.Y., Zheng, H., Miao, Q., Raman, S.S., Terzopoulos, D. & Sung, K. (2022) Cat‐net: A cross‐slice attention transformer model for prostate zonal segmentation in MRI. IEEE Transactions on Medical Imaging, 42(1), 291–303.
     [Google Scholar]
  20. Jiao, J., Tang, Y., Lin, K.‐L.C., Gao, Y., Ma, J., Wang, Y. & Zheng, W.‐S. (2023) Dilateformer: multi‐scale dilated transformer for visual recognition. IEEE Transactions on Multimedia, 25, 8906–8919.
     [Google Scholar]
  21. Lau, K.W., Po, L.‐M. & Rehman, Y. A.U. (2023) Large separable kernel attention: rethinking the large kernel attention design in CNN. Expert Systems and Applications, 236, 121352.
     [Google Scholar]
  22. Li, S., Liu, N., Li, F., Gao, J. & Ding, J. (2022) Automatic fault delineation in 3‐D seismic images with deep learning: data augmentation or ensemble learning?IEEE Transactions on Geoscience and Remote Sensing, 60, 1–14.
     [Google Scholar]
  23. Li, S., Yang, C., Sun, H. & Zhang, H. (2019) Seismic fault detection using an encoder‐decoder convolutional neural network with a small training set. Journal of Geophysics and Engineering, 16, 175–189.
     [Google Scholar]
  24. Li, X., Li, K., Xu, Z., Huang, Z. & Dou, Y. (2023) Fault‐SEG‐Net: a method for seismic fault segmentation based on multi‐scale feature fusion with imbalanced classification. Computers and Geotechnics, 158, 105412.
     [Google Scholar]
  25. Liu, N., He, T., Tian, Y., Wu, B., Gao, J. & Xu, Z. (2020) Common‐azimuth seismic data fault analysis using residual U‐Net. Interpretation, 8, SM25‐SM37.
     [Google Scholar]
  26. Ma, X., Yao, G., Zhang, F. & Wu, D. (2023) 3‐D seismic fault detection using recurrent convolutional neural networks with compound loss. IEEE Transactions on Geoscience and Remote Sensing, 61, 1–15.
     [Google Scholar]
  27. Marfurt, K.J., Kirlin, R.L., Farmer, S.L. & Bahorich, M.S. (1998) 3‐D seismic attributes using a semblance‐based coherency algorithm. Geophysics, 63, 1150–1165.
     [Google Scholar]
  28. Oktay, O., Schlemper, J., Folgoc, L.L., Lee, M.J., Heinrich, M.P., Misawa, K., Mori, K., McDonagh, S.G., Hammerla, N.Y., Kainz, B., Glocker, B. & Rueckert, D. (2018) Attention U‐Net: learning where to look for the pancreas. 2018 Computer Vision and Pattern Recognition. arXiv:1804.03999.
  29. Pedersen, S.I., Skov, T., Randen, T. & Sønneland, L. (2002) Automatic fault extraction using artificial ants. In the SEG technical program expanded abstracts 2002. Houston, TX: Society of Exploration Geophysicists, pp. 512–515.
  30. Ronneberger, O., Fischer, P. & Brox, T. (2015) U‐Net: convolutional networks for biomedical image segmentation. ArXiv, abs/1505.04597, 234–241.
     [Google Scholar]
  31. Sun, D.S., Ling, Y., Bai, X., Xi, X. (2011) Application of spectral decomposition and ant tracking to fractured carbonate reservoirs. In 73rd EAGE Conference and Exhibition incorporating SPE EUROPEC 2011. European Association of Geoscientists & Engineers, pp. cp–238.
  32. Van Bemmel, P.P. & Pepper, R.E.F. (2000) Seismic signal processing method and apparatus for generating a cube of variance Values. U.S. Patent 6151555A, Nov. 6.
  33. Vaswani, A., Shazeer, N.M., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, L. & Polosukhin, I. (2017) Attention is all you need. In Proceedings of the 31st International Conference on Neural Information processing systems. Red Hook, NY: Curran Associates, pp. 6000–6010.
  34. Woo, S., Park, J., Lee, J.‐Y. & Kweon, I.‐S. (2018) CBAM: convolutional block attention module. In Computer vision ‐ ECCV 2018. Cham: Springer, pp. 3‐1‐9. Also ArXiv, abs/1807.06521, 11211.
  35. Wu, W., Yang, Y., Wu, B., Ma, D., Tang, Z. & Yin, X. (2023) MTL‐FaultNet: seismic data reconstruction assisted multitask deep learning 3‐d fault interpretation. IEEE Transactions on Geoscience and Remote Sensing, 61, 1–15.
     [Google Scholar]
  36. Wu, X. & Fomel, S. (2018) Automatic fault interpretation with optimal surface voting. Geophysics, 83, O67–O82.
     [Google Scholar]
  37. Wu, X., Geng, Z., Shi, Y., Pham, N. & Fomel, S. (2019) Building realistic structure models to train convolutional neural networks for seismic structural interpretation. Geophysics, 85, WA27–WA39.
     [Google Scholar]
  38. Wu, X., Liang, L., Shi, Y. & Fomel, S. (2019) FaultSeg3D: using synthetic data sets to train an end‐to‐end convolutional neural network for 3d seismic fault segmentation. Geophysics, 84, 35–45.
     [Google Scholar]
  39. Wu, X. & Zhu, Z. (2017) Methods to enhance seismic faults and construct fault surfaces. Computers & Geosciences, 107, 37–48.
     [Google Scholar]
  40. Xu, J., Xiong, Z. & Bhattacharyya, S. (2023) PIDNet: a real‐time semantic segmentation network inspired by PID controllers. In the 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Piscataway, NJ: IEEE, pp. 19529–19539.
  41. Zhang, T., Lin, Y., Liu, K.H., Alhakeem, A. & Gao, S.S. (2017) Fault visualization enhancement using ant tracking technique and its application in the Taranaki Basin, New Zealand. In the SEG technical program expanded abstracts 2017. Houston, TX: Society of Exploration Geophysicists, pp. 1150–1165.
  42. Zheng, J., Liu, H., Feng, Y., Xu, J. & Zhao, L. (2023) CASF‐Net: cross‐attention and cross‐scale fusion network for medical image segmentation. Computer Methods and Programs in Biomedicine, 229, 107307.
     [Google Scholar]
/content/journals/10.1111/1365-2478.13655
Loading
A hybrid network for three‐dimensional seismic fault segmentation based on nested residual attention and self‐attention mechanism
Geophysical Prospecting 73, 575 (2025); https://doi.org/10.1111/1365-2478.13655
/content/journals/10.1111/1365-2478.13655
/content/journals/10.1111/1365-2478.13655
Loading

Data & Media loading...

  • Article Type: Research Article
Keyword(s): 3D; faults; interpretation

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