1887
Volume 74, Issue 1
  • E-ISSN: 1365-2478

Abstract

ABSTRACT

Enhancing seismic data resolution is a crucial step for geological interpretation and imaging. Deep learning‐driven resolution enhancement primarily depends on sophisticated network architectures and extensive datasets. A lightweight seismic super‐resolution model based on contrastive learning and knowledge distillation is proposed. Knowledge distillation is implemented by training a compact student network to mimic a powerful teacher model, thereby reducing reliance on extensive datasets and complex architectures. Contrastive learning is leveraged to align the bottleneck features encoded from the teacher network with the ones from the student network across different noisy inputs. The student network's total loss comprises a supervised loss with ground‐truth labels, a distillation loss with the teacher's pseudo‐labels and a feature‐matching loss derived from the bottleneck features of both networks. The comparative experiments were conducted on four field datasets and 3200 pairs of slices extracted from 800 pairs of synthetic three‐dimensional seismic cubes. Experimental results demonstrate that the proposed model achieves similar to or better performance than the comparison models for noise suppression and weak signal recovery, even with only parameters and training data compared to the reference model.

© 2026 European Association of Geoscientists & Engineers. © 2026 European Association of Geoscientists & Engineers.
Loading

Article metrics loading...

/content/journals/10.1111/1365-2478.70129
2026-01-20
2026-02-19

  • From This Site

    /content/journals/10.1111/1365-2478.70129
    dcterms_title,dcterms_subject,pub_keyword
    -contentType:Journal -contentType:Contributor -contentType:Concept -contentType:Institution
    10
    5
Loading full text...

Full text loading...

References

  1. Baysal, E., D. D.Kosloff, and J. W.Sherwood. 1983. “Reverse Time Migration.” Geophysics48, no. 11: 1514–1524.
     [Google Scholar]
  2. Braga, I. L. S., and F. S.Moraes. 2013. “High‐Resolution Gathers by Inverse Q Filtering in the Wavelet Domain.” Geophysics78, no. 2: V53–V61.
     [Google Scholar]
  3. Cadzow, J. A., and X. K.Li. 1995. “Blind Deconvolution.” Digital Signal Processing5, no. 1: 3–20.
     [Google Scholar]
  4. Chen, T., S.Kornblith, K.Swersky, M.Norouzi, and G. E.Hinton. 2020. “Big Self‐Supervised Models Are Strong Semi‐Supervised Learners.” Advances in Neural Information Processing Systems33: 22243–22255.
     [Google Scholar]
  5. Diederik, P. K., and B.Jimmy. 2014. Adam: A Method for Stochastic Optimization. Preprint arXiv, December 22. https://doi.org/10.48550/arXiv.1412.6980.
  6. Dou, Y.‐M., and K.‐W.Li. 2024. “3D Seismic Fault Detection via Contrastive‐Reconstruction Representation Learning.” Expert Systems With Applications249: 123617.
     [Google Scholar]
  7. Einar, K.1979. “Constant Q‐Wave Propagation and Attenuation.” Journal of Geophysical Research84, no. B9: 4737.
     [Google Scholar]
  8. Feng, Q.‐K., S.Wang, and Y.Li. 2024. “Efficient Signal‐to‐Noise Ratio Enhancement Model for Severely Contaminated Distributed Acoustic Sensing Seismic Data Based on Heterogeneous Knowledge Distillation.” Geophysics89, no. 3: V197–V208.
     [Google Scholar]
  9. Gao, Y., D.‐F.Zhao, T.‐H.Li, G.‐F.Li, and S.‐W.Guo. 2023. “Deep Learning Vertical Resolution Enhancement Considering Features of Seismic Data.” IEEE Transactions on Geoscience and Remote Sensing61: 1–13.
     [Google Scholar]
  10. He, K.‐M., H.‐Q.Fan, Y.‐X.Wu, S.‐N.Xie, and R.Girshick. 2020. Momentum Contrast for Unsupervised Visual Representation Learning. In the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 9726–9735. IEEE.
  11. Hinton, G., O.Vinyals, and J.Dean. 2015. “Distilling the Knowledge in a Neural Network.” Preprint arXiv, March 9. https://doi.org/10.48550/arXiv.1503.02531.
  12. Kokilepersaud, K., M.Prabhushankar, and G.AlRegib. 2022. Volumetric Supervised Contrastive Learning for Seismic Semantic Segmentation. In Second International Meeting for Applied Geoscience & Energy, 1699–1703. Society of Exploration Geophysicists.
  13. Li, J.‐H., and X.‐L.Wu. 2022. “Simple Framework for the Contrastive Learning of Visual Representations‐Based Data‐Driven Tight Frame for Seismic Denoising and Interpolation.” Geophysics87, no. 5: V467–V480.
     [Google Scholar]
  14. Li, J.‐T., X.‐M.Wu, and Z.‐X.Hu. 2022. “Deep Learning for Simultaneous Seismic Image Super‐Resolution and Denoising.” IEEE Transactions on Geoscience and Remote Sensing60, no. 1: 1–11.
     [Google Scholar]
  15. Li, J.‐T., X.‐M.Wu, and Y.‐M.Ye, et al. 2023. “Unsupervised Contrastive Learning for Seismic Facies Characterization.” Geophysics88, no. 1: WA81–WA89.
     [Google Scholar]
  16. Li, K.‐R., J.‐M.Song, and S.Xia, et al. 2023. “Salt Structure Identification Based on U‐Net Model With Target Flip, Multiple Distillation and Self‐Distillation Methods.” Frontiers in Earth Science10: 1071637.
     [Google Scholar]
  17. Li, K.‐W., W.‐L.Liu, Y.‐M.Dou, Z.‐F.Xu, H.‐J.Duan, and R.‐L.Jing. 2023. “CONSS: Contrastive Learning Method for Semi‐Supervised Seismic Facies Classification.” IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing16: 7838–7849.
     [Google Scholar]
  18. Li, Y., G.‐L.Zhang, and J.Duan, et al. 2020. “Extended Stable Factor Method for the Inverse Q‐Filter.” Geophysics85, no. 3: T155–T163.
     [Google Scholar]
  19. Lin, L., Z.Zhong, C.‐Y.Cai, C.‐L.Li, and H.Zhang. 2024. “SeisGAN: Improving Seismic Image Resolution and Reducing Random Noise Using a Generative Adversarial Network.” Mathematical Geosciences56, no. 4: 723–749.
     [Google Scholar]
  20. Liu, C.‐W., M.‐Y.Sun, and N.‐X.Dai, et al. 2022. “Deep Learning‐Based Point‐Spread Function Deconvolution for Migration Image Deblurring.” Geophysics87, no. 4: S249–S265.
     [Google Scholar]
  21. Liu, N.‐H., Y.‐X.Zhang, Y.Yang, R.‐C.Liu, J.‐H.Gao, and N.Zhang. 2024. “Application of Sparse S Transform Network With Knowledge Distillation in Seismic Attenuation Delineation.” Petroleum Science21, no. 4: 2345–2355.
     [Google Scholar]
  22. Lu, J., C.‐L.Wu, J.‐P.Huang, G.‐L.Li, and S.‐Z.Yuan. 2024. “Multi‐receptive Field Distillation Network for Seismic Velocity Model Building.” Engineering Applications of Artificial Intelligence133: 108547.
     [Google Scholar]
  23. Min, F., L.‐R.Wang, S.‐L.Pan, and G.‐J.Song. 2023. “D2UNet: Dual Decoder U‐Net for Seismic Image Super‐Resolution Reconstruction.” IEEE Transactions on Geoscience and Remote Sensing61: 1–13.
     [Google Scholar]
  24. Niloofar, A., R. K.Amin, K. R.Abolghasem, and S.Mehrdad. 2018. “Seismic Resolution Enhancement Using Scale Transform in the Time‐Frequency Domain.” Geophysics83, no. 6: V305–V314.
     [Google Scholar]
  25. Park, J., O.Saad, J.Oh, and T.Alkhalifah. 2024. Efficient Transformer for Seismic Image Enhancement. In the 85th EAGE Annual Conference & Exhibition (including the Workshop Programme), 6: 1–5. EAGE.
  26. Shang, X.‐M., R.Diao, Y.‐P.Feng, and C.‐X.Zhao. 2014. “The Application of Spectral Modeling Method to High Resolution Processing of Seismic Data.” Geophysical and Geochemical Exploration63, no. 4: 75–80.
     [Google Scholar]
  27. Si, X., X.‐M.Wu, H.‐L.Sheng, J.Zhu, and Z.‐F.Li. 2024. “SeisCLIP: A Seismology Foundation Model Pre‐Trained by Multi‐Modal Data for Multi‐Purpose Seismic Feature Extraction.” IEEE Transactions on Geoscience and Remote Sensing62: 1–13.
     [Google Scholar]
  28. Sun, Q.‐F., J.‐Y.Xu, H.‐X.Zhang, Y.‐X.Duan, and Y.‐K.Sun. 2022. “Random Noise Suppression and Super‐Resolution Reconstruction Algorithm of Seismic Profile Based on GAN.” >Journal of Petroleum Exploration and Production Technology12: 2107–2119.
     [Google Scholar]
  29. Tarantola, A.1984. “Inversion of Seismic Reflection Data in the Acoustic Approximation.” Geophysics49, no. 8: 1259–1266.
     [Google Scholar]
  30. van den Oord, A., Y.‐Z.Li, and O.Vinyals. 2018. Representation Learning With Contrastive Predictive Coding. Preprint. arXiv, July 10. https://doi.org/10.48550/arXiv.1807.03748.
  31. Wang, X.‐J., B.‐S.Chen, and S.‐Y.Cao. 2009. “Research and Application of HHT Amplitude Frequency Recovery Processing Technology.” China Offshore Oil and Gas1, no. 1: 19–22.
     [Google Scholar]
  32. Wang, Y.‐X., J.‐Y.Xu, Z.‐C.Zhao, Y.Gao, and H.Zhang. 2024. “Structurally‐Constrained Unsupervised Deep Learning for Seismic High‐Resolution Reconstruction.” IEEE Transactions on Geoscience and Remote Sensing62: 1–15.
     [Google Scholar]
  33. Wang, Z., A. C.Bovik, H. R.Sheikh, and E. P.Simoncelli. 2004. “Image Quality Assessment: From Error Visibility to Structural Similarity.” IEEE Transactions on Image Processing13, no. 4: 600–612.
     [Google Scholar]
  34. Wu, X.‐M., and D.Hale. 2016. “3D Seismic Image Processing for Faults.” Geophysics81, no. 2: IM1–IM11.
     [Google Scholar]
  35. Yang, Z., H.‐L.Li, X.‐G.Tuo, L.‐J.Li, and J.‐N.Wen. 2023. “Unsupervised Clustering of Microseismic Signals Using a Contrastive Learning Model.” IEEE Transactions on Geoscience and Remote Sensing61: 1–12.
     [Google Scholar]
  36. Yuan, Z.‐Y., Y.‐X.Jiang, Z.‐L.An, W.‐B.Ma, and Y.Wang. 2024. “Seismic Resolution Improving by a Sequential Convolutional Neural Network.” PloS ONE19, no. 6: e0304981.
     [Google Scholar]
  37. Zeng, D., Q.Xu, S.‐L.Pan, G.‐J.Song, and F.Min. 2023. “Seismic Image Super‐Resolution Reconstruction Through Deep Feature Mining Network.” Applied Intelligence53, no. 19: 21875–21890.
     [Google Scholar]
  38. Zhang, K., Y.‐D.Li, G.‐Z.Liu, and Y.‐L.Jia. 1999. “Multi‐Resolution Seismic Signal Deconvolution.” Chinese Journal of Geophysics42, no. 4: 529–535.
     [Google Scholar]
  39. Zhou, R.‐S., C.Zhou, Y.‐J.Wang, X.‐M.Yao, G.‐M.Hu, and F.‐C.Yu. 2023. “Deep Learning With Fault Prior for 3‐D Seismic Data Super‐Resolution.” IEEE Transactions on Geoscience and Remote Sensing61: 1–16.
     [Google Scholar]
/content/journals/10.1111/1365-2478.70129
Loading
CKDSR: Seismic Super‐Resolution Through Contrastive Knowledge Distillation
Geophysical Prospecting 74, e70129 (2026); https://doi.org/10.1111/1365-2478.70129
/content/journals/10.1111/1365-2478.70129
/content/journals/10.1111/1365-2478.70129
Loading

Data & Media loading...

  • Article Type: Research Article
Keyword(s): contrastive learning; deep learning; knowledge distillation; seismic resolution enhancement

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