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

Abstract

Abstract

Post‐stack data are susceptible to noise interference and have low resolution, which impacts the accuracy and efficiency of subsequent seismic data interpretation. To address this issue, we propose a deep learning approach called Seis‐SUnet, which achieves simultaneous random noise suppression and super‐resolution reconstruction of seismic data. First, the Conv‐Swin‐Block is designed to utilize ordinary convolution and Swin transformer to capture the long‐distance dependencies in the spatial location of seismic data, enabling the network to comprehensively comprehend the overall structure of seismic data. Second, to address the problem of weakening the effective signal during network mapping, we use a hybrid training strategy of L1 loss, edge loss and multi‐scale structural similarity loss. The edge loss function directs the network training to focus more on the high‐frequency information at the edges of seismic data by amplifying the weight. Additionally, the verification of synthetic and field seismic datasets confirms that Seis‐SUnet can effectively improve the signal‐to‐noise ratio and resolution of seismic data. By comparing it with traditional methods and two deep learning reconstruction methods, experimental results demonstrate that Seis‐SUnet excels in removing random noise, preserving the continuity of rock layers and maintaining faults as well as being strong robustness.

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

Article metrics loading...

/content/journals/10.1111/1365-2478.13617
2025-01-26
2025-12-10

  • From This Site

    /content/journals/10.1111/1365-2478.13617
    dcterms_title,dcterms_subject,pub_keyword
    -contentType:Journal -contentType:Contributor -contentType:Concept -contentType:Institution
    10
    5
Loading full text...

Full text loading...

References

  1. Cao, H., Wang, Y., Chen, J., Jiang, D., Zhang, X., Tian, Q. & Wang, M. (2021) Swin‐unet: Unet‐like pure transformer for medical image segmentation. Lecture Notes in Computer Science, 13803, 205–218. DOI: 10.48550/arXiv.2105.05537.
     [Google Scholar]
  2. Chen, G., Liu, Y. & Zhang, M. (2023) Unsupervised deep learning for seismic data reconstruction. In: Third international meeting for applied geoscience & energy expanded abstracts. Houston, TX: Society of Exploration Geophysicists, 1578–1582.
  3. Chen, G.Y., Xie, W. & Krzyzak, A. (2023) Improved blind image denoising with dncnn. In Huang, D.‐S., Premaratne, P., Jin, B., Qu, B., Jo, K.‐H. & Hussain, A. (Eds.) Advanced intelligent computing technology and applications. Singapore: Springer Nature Singapore, pp. 263–271.
  4. Chen, S. & Wang, Y. (2018) Seismic resolution enhancement by frequency‐dependent wavelet scaling. IEEE Geoscience and Remote Sensing Letters, 15(5), 654–658.
     [Google Scholar]
  5. Chen, Y. & Ma, J. (2014) Random noise attenuation by f−x$f-x$ empirical‐mode decomposition predictive filtering. Geophysics, 79, V81–V91.
     [Google Scholar]
  6. Deng, M.‐D., Jia, R.‐S., Sun, H.‐M. & Zhang, X.‐L. (2021) Super‐resolution reconstruction of seismic section image via multi‐scale convolution neural network. E3S Web of Conferences, 303, 01058.
     [Google Scholar]
  7. Ebadi, M. (2017) Coherent and incoherent seismic noise attenuation using parabolic radon transform and its application in environmental geophysics. Modeling Earth Systems and Environment, 3, 18.
     [Google Scholar]
  8. Faleide, T.S., Braathen, A., Lecomte, I., Mulrooney, M.J., Midtkandal, I., Bugge, A.J. & Planke, S. (2021) Impacts of seismic resolution on fault interpretation: insights from seismic modelling. Tectonophysics, 816, 229008.
     [Google Scholar]
  9. Han, W., Zhou, Y. & Chi, Y. (2018) Deep learning convolutional neural networks for random noise attenuation in seismic data. Geophysical Prospecting for Petroleum, 57(6), 862–869.
     [Google Scholar]
  10. Hao, Y., Huang, H., Gao, J. & Zhang, S. (2019) Inversion‐based time‐domain inverse q$q$ ‐filtering for seismic resolution enhancement. IEEE Geoscience and Remote Sensing Letters, 16(12), 1934–1938.
     [Google Scholar]
  11. Jun, W., Xin, Z., Houde, Z. & Yinghui, W. (2020) Seismic data reconstruction based on super resolution convolutional neural network. Houston, TX: Society of Exploration Geophysicists, pp. 38–42.
  12. Li, B., Liu, Y. & Liu, C. (2017) . Geophysics, 83 (4), F41–F48. doi: https://doi.org/10.1190/geo2017‐0322.1
  13. Li, J., Wu, X. & Hu, Z. (2022) Deep learning for simultaneous seismic image super‐resolution and denoising. IEEE Transactions on Geoscience and Remote Sensing, 60, 1–11.
     [Google Scholar]
  14. Li, J.‐H., Zhang, Y.‐J., Qi, R. & Liu, Q.H. (2017) Wavelet‐based higher order correlative stacking for seismic data denoising in the curvelet domain. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 10(8), 3810–3820.
     [Google Scholar]
  15. Li, W. & Wang, J. (2021) Residual learning of cycle‐GAN for seismic data denoising. IEEE Access, 9, 11585–11597.
     [Google Scholar]
  16. Lim, B., Son, S., Kim, H., Nah, S. & Lee, K.M. (2017) Enhanced deep residual networks for single image super‐resolution. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW). Piscataway, NJ: IEEE, pp. 1132–1140.
  17. Lin, L., Zhong, Z., Cai, C., Li, C. & Zhang, H. (2024) SeisGAN: improving seismic image resolution and reducing random noise using a generative adversarial network. Mathematical Geosciences, 56, 723–749.
     [Google Scholar]
  18. Liu, Y., Wu, G. & Zheng, Z. (2021) Seismic data interpolation without iteration using a t‐x‐y streaming prediction filter with varying smoothness. Geophysics, 87(1), V29–V38.
     [Google Scholar]
  19. Liu, Y. & Zheng, Z. (2022) Noniterative f ‐x‐y streaming prediction filtering for random noise attenuation on seismic data. IEEE Transactions on Geoscience and Remote Sensing, 60, 1–9.
     [Google Scholar]
  20. Liu, Z., Lin, Y., Cao, Y., Hu, H., Wei, Y., Zhang, Z., Lin, S. & Guo, B. (2021) Swin transformer: Hierarchical vision transformer using shifted windows. In: 2021 IEEE/CVF International Conference on Computer Vision (ICCV). Piscataway, NJ: IEEE, 9992–10002.
  21. Lu, Y., Huang, Y., Xue, W. & Zhang, G. (2019) Seismic data processing method based on wavelet transform for de‐noising. Cluster Computing, 22, 6609–6620.
     [Google Scholar]
  22. Manenti, R.R., Souza, W.E. & Porsani, M.J. (2018) Spectral whitening based on the singular spectral analysis method. Journal of Geophysics and Engineering, 15(4), 1460–1469.
     [Google Scholar]
  23. Min, F., Wang, L., Pan, S. & Song, G. (2023) D2unet: dual decoder u‐net for seismic image super‐resolution reconstruction. IEEE Transactions on Geoscience and Remote Sensing, 61, 1–13.
     [Google Scholar]
  24. Min, F., Wang, L., Pan, S. & Song, G.J. (2021) Ddae‐GAN: seismic data denoising by integrating autoencoder and generative adversarial network. In: Rough Sets: Proceedings of the International Joint Conference, IJCRS 2021. Berlin: Springer, 44–56.
  25. Oboué, Y. A. S.I., Chen, Y., Fomel, S., Zhong, W. & Chen, Y. (2024) An advanced median filter for improving the signal‐to‐noise ratio of seismological datasets. Computers & Geosciences, 182, 105464.
     [Google Scholar]
  26. Onajite, E. (2014) Chapter 13 ‐ understanding seismic interpretation methodology. In: Onajite, E. (Ed.) seismic data analysis techniques in hydrocarbon exploration. Oxford: Elsevier, pp. 177–211.
  27. Ronneberger, O., Fischer, P. & Brox, T. (2015) U‐net: convolutional networks for biomedical image segmentation. Lecture Notes in Computer Science(), vol 9351. Springer, Cham. https://doi.org/10.1007/978‐3‐319‐24574‐4_28
  28. Schroeder, F.W., Martínez, G.C., Shalaby, H., der Toorn, J.V., de Souza, J.A., van der Molen, M., Oaubel, M., Ragab, R., Avakian, R. & Aung, Z.W. (2021) Chapter 2 ‐ qualitative seismic interpretation. In: Onajite, E. (Ed.) Applied techniques to integrated oil and gas reservoir characterization. Oxford: Elsevier, pp. 39–71.
  29. Shao, D., Zhao, Y., Li, Y. & Li, T. (2022) Noisy2noisy: denoise pre‐stack seismic data without paired training data with labels. IEEE Geoscience and Remote Sensing Letters, 19, 1–5.
     [Google Scholar]
  30. Silva, R.M.D.G., Baroni, L., Ferreira, R.S., Civitarese, D., Szwarcman, D. & Brazil, E.V. (2019) Netherlands dataset: A new public dataset for machine learning in seismic interpretation. DOI:10.48550/arXiv.1904.00770.
  31. Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, Ł. & Polosukhin, I. (2017) Attention is all you need. Advances in Neural Information Processing Systems, 30, 6000–6010.
     [Google Scholar]
  32. Wang, B., Zhang, N., Lu, W. & Wang, J. (2019) Deep‐learning‐based seismic data interpolation: a preliminary result. Geophysics, 84(1), V11–V20.
     [Google Scholar]
  33. Wang, C. & Wang, Y. (2021) Robust singular value decomposition filtering for low signal‐to‐noise ratio seismic data. Geophysics, 86(3), V233–V244.
     [Google Scholar]
  34. Wang, D., Chen, G., Chen, J. & Cheng, Q. (2024) Seismic data denoising using a self‐superviseddeep learning network. Mathematical Geosciences, 56, 487–510.
     [Google Scholar]
  35. Wang, Q., Gao, J., Liu, N. & Jiang, X. (2018) High‐resolution seismic time‐frequency analysis using the synchrosqueezing generalized s‐transform. IEEE Geoscience and Remote Sensing Letters, 15(3), 374–378.
     [Google Scholar]
  36. Wang, Z., Simoncelli, E. & Bovik, A. (2003) Multiscale structural similarity for image quality assessment. In: The Thirty‐Seventh Asilomar Conference on Signals, Systems & Computers, 2003, volume 2. Piscataway, NJ: IEEE, pp. 1398–1402.
  37. Woo, S., Park, J., Lee, J.‐Y. & Kweon, I.S. (2018) Cbam: Convolutional block attention module. In Ferrari, V., Hebert, M., Sminchisescu, C. & Weiss, Y. (Eds.) Computer vision – ECCV 2018. Cham. Springer International, pp. 3–19.
     [Google Scholar]
  38. Xu, Z., Luo, Y., Wu, B. & Meng, D. (2023) S2S‐WTV: seismic data noise attenuation using weighted total variation regularized self‐supervised learning. IEEE Transactions on Geoscience and Remote Sensing, 61, 1–15.
     [Google Scholar]
  39. Yao, Z., Shen, C., Li, J., Li, Y. & Chen, N. (2023) A novel seismic random noise suppression method based on wavelet threshold and Lipschitz. Journal of Applied Geophysics, 217, 105178.
     [Google Scholar]
  40. Yuan, Y., Li, Y. & Zhou, S. (2021) Multichannel statistical broadband wavelet deconvolution for improving resolution of seismic signals. IEEE Transactions on Geoscience and Remote Sensing, 59(2), 1772–1783.
     [Google Scholar]
  41. Zhang, M., Liu, Y., Zhang, H. & Chen, Y. (2020) Incoherent noise suppression of seismic data based on robust low‐rank approximation. IEEE Transactions on Geoscience and Remote Sensing, 58(12), 8874–8887.
     [Google Scholar]
  42. Zhang, Q., Wang, H., Chen, W. & Huang, G. (2021) A local radon transform for seismic random noise attenuation. Journal of Applied Geophysics, 186, 104264.
     [Google Scholar]
  43. Zhang, Y., Li, K., Li, K., Wang, L., Zhong, B. & Fu, Y.R. (2018) Image super‐resolution using very deep residual channel attention networks. Lecture Notes in Computer Science, vol 11211. https://doi.org/10.1007/978‐3‐030‐01234‐2_18
/content/journals/10.1111/1365-2478.13617
Loading
Removing random noise and improving the resolution of seismic data using deep‐learning transformers
Geophysical Prospecting 73, 611 (2025); https://doi.org/10.1111/1365-2478.13617
/content/journals/10.1111/1365-2478.13617
/content/journals/10.1111/1365-2478.13617
Loading

Data & Media loading...

  • Article Type: Research Article
Keyword(s): Deep learning; Feature extraction; Seismic data denoising; Seismic profile; Super‐resolution reconstruction; Swin transformer; Unet model

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