1887
Volume 72, Issue 5
  • E-ISSN: 1365-2478

Abstract

Abstract

The presence of coherent noise in seismic data leads to errors and uncertainties, and as such it is paramount to suppress noise as early and efficiently as possible. Self‐supervised denoising circumvents the common requirement of deep learning procedures of having noisy‐clean training pairs. However, self‐supervised coherent noise suppression methods require extensive knowledge of the noise statistics. We propose the use of explainable artificial intelligence approaches to ‘see inside the black box’ that is the denoising network and use the gained knowledge to replace the need for any prior knowledge of the noise itself. This is achieved in practice by leveraging bias‐free networks and the direct linear link between input and output provided by the associated Jacobian matrix; we show that a simple averaging of the Jacobian contributions over a number of randomly selected input pixels provides an indication of the most effective mask to suppress noise present in the data. The proposed method, therefore, becomes a fully automated denoising procedure requiring no clean training labels or prior knowledge. Realistic synthetic examples with noise signals of varying complexities, ranging from simple time‐correlated noise to complex pseudo‐rig noise propagating at the velocity of the ocean, are used to validate the proposed approach. Its automated nature is highlighted further by an application to two field data sets. Without any substantial pre‐processing or any knowledge of the acquisition environment, the automatically identified blind masks are shown to perform well in suppressing both trace‐wise noise in common shot gathers from the Volve marine data set and coloured noise in post‐stack seismic images from a land seismic survey.

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

Article metrics loading...

/content/journals/10.1111/1365-2478.13480
2024-05-21
2026-02-19

  • From This Site

    /content/journals/10.1111/1365-2478.13480
    dcterms_title,dcterms_subject,pub_keyword
    -contentType:Journal -contentType:Contributor -contentType:Concept -contentType:Institution
    10
    5
Loading full text...

Full text loading...

References

  1. Benkert, R., Joseph Aribido, O. & AlRegib, G. (2021) Explainable seismic neural networks using learning statistics. In First International Meeting for Applied Geoscience & Energy. Houston, TX: Society of Exploration Geophysicists, pp. 1425–1429.
     [Google Scholar]
  2. Birnie, C. & Alkhalifah, T. (2022) Transfer learning for self‐supervised, blind‐spot seismic denoising. Frontiers in Earth Science, 10, 1053279.
     [Google Scholar]
  3. Birnie, C., Ravasi, M., Liu, S. & Alkhalifah, T. (2021) The potential of self‐supervised networks for random noise suppression in seismic data. Artificial Intelligence in Geosciences, 2, 47–59.
     [Google Scholar]
  4. Broaddus, C., Krull, A., Weigert, M., Schmidt, U. & Myers, G. (2020) Removing structured noise with self‐supervised blind‐spot networks. In 2020 IEEE 17th International Symposium on Biomedical Imaging (ISBI). Piscataway, NJ: IEEE, pp. 159–163.
     [Google Scholar]
  5. Buades, A., Coll, B. & Morel, J.‐M. (2005) A non‐local algorithm for image denoising. In 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05), volume 2. Piscataway, NJ: IEEE, pp. 60–65.
     [Google Scholar]
  6. Chamorro, D., Zhao, J., Birnie, C., Staring, M., Moritz, F. & Ravasi, M. (2023) Deep learning‐based extraction of surface wave dispersion curves from seismic shot gathers. arXiv [preprint]. arXiv:2305.13990.
  7. Dong, X., Wang, H., Zhong, T. & Li, Y. (2021) Desert mixed seismic noise suppression by using multiple forward models and a supervised deep‐learning method. Exploration Geophysics, 52(4), 431–445.
     [Google Scholar]
  8. Hamidi, R., Latif, A.H. & Lee, W.Y. (2020) Autoencoder neural network application for coherent noise attenuation in high frequency shallow marine seismic data. In Offshore Technology Conference Asia. Houston, TX: OTC, pp. D012S001R086.
     [Google Scholar]
  9. Kaur, H., Fomel, S. & Pham, N. (2020) Seismic ground‐roll noise attenuation using deep learning. Geophysical Prospecting, 68(7), 2064–2077.
     [Google Scholar]
  10. Krull, A., Buchholz, T.‐O. & Jug, F. (2019) Noise2void‐learning denoising from single noisy images. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, pp. 2129–2137.
     [Google Scholar]
  11. Laine, S., Karras, T., Lehtinen, J. & Aila, T. (2019) High‐quality self‐supervised deep image denoising. Advances in Neural Information Processing Systems, 32, 6970–6980.
     [Google Scholar]
  12. Li, C., Guo, C., Han, L., Jiang, J., Cheng, M.‐M., Gu, J. & Loy, C.C. (2021) Low‐light image and video enhancement using deep learning: a survey. IEEE Transactions on Pattern Analysis and Machine Intelligence, 44(12), 9396–9416.
     [Google Scholar]
  13. Liu, S., Birnie, C. & Alkhalifah, T. (2022) Coherent noise suppression via a self‐supervised blind‐trace deep learning scheme. arXiv [preprint], arXiv:2206.00301.
  14. Luiken, N., Ravasi, M. & Birnie, C.E. (2022) A hybrid approach to seismic deblending: when physics meets self‐supervision. arXiv [preprint], arXiv:2205.15395.
  15. Markovic, M., Malehmir, R. & Malehmir, A. (2022) Diffraction pattern recognition using deep semantic segmentation. Near Surface Geophysics, 20(5), 507–518.
     [Google Scholar]
  16. Mohan, E., Rajesh, A., Sunitha, G., Konduru, R.M., Avanija, J. & Ganesh Babu, L. (2021) A deep neural network learning‐based speckle noise removal technique for enhancing the quality of synthetic‐aperture radar images. Concurrency and Computation: Practice and Experience, 33(13), e6239.
     [Google Scholar]
  17. Mohan, S., Kadkhodaie, Z., Simoncelli, E.P. & Fernandez‐Granda, C. (2020) Robust and interpretable blind image denoising via bias‐free convolutional neural networks. In International Conference on Learning Representations. Appleton, WI: ICLR. arXiv preprint arXiv:1906.05478. 2019 Jun 13.
     [Google Scholar]
  18. Mosser, L. & Alaei, B. (2022) Deep learning‐based unsupervised denoising for coherent noise attenuation in seismic data. In Second EAGE Subsurface Intelligence Workshop, volume 2022. Houten, the Netherlands: EAGE, pp. 1–5.
     [Google Scholar]
  19. Noh, K., Kim, D. & Byun, J. (2023) Intrinsically explainable deep learning for supervised seismic facies classification using intrinsic method. IEEE Transactions on Geoscience and Remote Sensing, 61, 1–10.
     [Google Scholar]
  20. Qian, F., Guo, W., Liu, Z., Yu, H., Zhang, G. & Hu, G. (2022) Unsupervised erratic seismic noise attenuation with robust deep convolutional autoencoders. IEEE Transactions on Geoscience and Remote Sensing, 60, 1–16.
     [Google Scholar]
  21. Ravasi, M., Selvan, T. & Luiken, N. (2022) Stochastic multi‐dimensional deconvolution. IEEE Transactions on Geoscience and Remote Sensing, 60, 1–14.
     [Google Scholar]
  22. Saad, O.M. & Chen, Y. (2020) Deep denoising autoencoder for seismic random noise attenuation. Geophysics, 85(4), V367–V376.
     [Google Scholar]
  23. Suzuki, K. (2017) Overview of deep learning in medical imaging. Radiological Physics and Technology, 10(3), 257–273.
     [Google Scholar]
  24. Wang, S., Hu, W., Yuan, P., Wu, X., Zhang, Q., Nadukandi, P., Ocampo Botero, G. & Chen, J. (2021) Seismic deblending by self‐supervised deep learning with a blind‐trace network. In SEG/AAPG/SEPM First International Meeting for Applied Geoscience & Energy. OnePetro, pp. 3194–3198.
     [Google Scholar]
  25. Zhao, Y., Li, Y., Dong, X. & Yang, B. (2018) Low‐frequency noise suppression method based on improved dncnn in desert seismic data. IEEE Geoscience and Remote Sensing Letters, 16(5), 811–815.
     [Google Scholar]
  26. Zhong, T., Cheng, M., Lu, S., Dong, X. & Li, Y. (2021) Rcen: a deep‐learning‐based background noise suppression method for DAS‐VSP records. IEEE Geoscience and Remote Sensing Letters, 19, 1–5.
     [Google Scholar]
/content/journals/10.1111/1365-2478.13480
Loading
Explainable artificial intelligence‐driven mask design for self‐supervised seismic denoising
Geophysical Prospecting 72, 1729 (2024); https://doi.org/10.1111/1365-2478.13480
/content/journals/10.1111/1365-2478.13480
/content/journals/10.1111/1365-2478.13480
Loading

Data & Media loading...

  • Article Type: Research Article
Keyword(s): data processing; neural network; noise; seismic data processing; seismic processing; signal processing; signal‐to‐noise ratio

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