1887
Volume 74, Issue 2
  • E-ISSN: 1365-2478

Abstract

ABSTRACT

We propose an improved TransUNet‐based seismic data reconstruction method, designed to address the issue of seismic data loss resulting from factors such as instrument failures and environmental interference during acquisition, while overcoming the inadequacy of existing deep learning methods in capturing local details during reconstruction. First, the method applies amplitude consistency correction on the training data. By standardizing the distribution of data amplitude features, it effectively enhances the model's adaptability to seismic data under different scenarios and acquisition conditions, thereby improving generalization performance. On this basis, a dynamic mask prediction mechanism is introduced. Through accurately locating data‐missing regions, it guides the network to focus on the parts to be reconstructed, reduces excessive interference with the original valid signals and further prevents the destruction of effective information. Meanwhile, the method integrates the global feature extraction capability of the transformer and the local feature preservation advantage of the U‐Net. It can not only capture long‐distance structural correlations in seismic data but also finely retain local stratigraphic details. To further enhance the targeting of feature expression, the Convolutional Block Attention Module (CBAM) is incorporated into the method. Although it exhibits relatively low innovativeness in the current version, it can assist the network in more efficiently integrating local and global information and enhancing the collaborative feature expression capability—achieved through the channel attention module's weighting of key feature channels and the spatial attention module's focusing on important regions—thus holding certain necessity. The performance of the method was validated using SEG‐C3 synthetic data and real seismic data under both irregular and regular missing scenarios. Compared with commonly used methods, the proposed method can effectively recover detailed information and outperforms other methods in metrics such as signal‐to‐noise ratio (SNR), peak signal‐to‐noise ratio (PSNR), structural similarity index (SSIM) and root‐mean‐square error (RMSE). Further verification via FK (frequency wavenumber) spectrum analysis and single‐trace amplitude error analysis confirms the consistency between the reconstruction results of the proposed method and the original data. This method provides a high‐precision and strong generalization solution for missing seismic data reconstruction, with promising application prospects.

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

Article metrics loading...

/content/journals/10.1111/1365-2478.70137
2026-02-15
2026-03-13

  • From This Site

    /content/journals/10.1111/1365-2478.70137
    dcterms_title,dcterms_subject,pub_keyword
    -contentType:Journal -contentType:Contributor -contentType:Concept -contentType:Institution
    10
    5
Loading full text...

Full text loading...

References

  1. Abedi, M. M., and D.Pardo. 2022. “A Multidirectional Deep Neural Network for Self‐Supervised Reconstruction of Seismic Data.” IEEE Transactions on Geoscience and Remote Sensing60: 1–9. https://doi.org/10.1109/tgrs.2022.3227212.
     [Google Scholar]
  2. Cao, J., L.Fu, W.Fang, and M.Wu. 2024. “Seismic Data Interpolation via Unet With Non‐Local Blocks.” Exploration Geophysics55, no. 3: 213–222. https://doi.org/10.1080/08123985.2023.2290134.
     [Google Scholar]
  3. Chen, J., Y.Lu, Q.Yu, et al. 2021. “TransUNet: Transformers Make Strong Encoders for Medical Image Segmentation.” arXiv. https://www.engineeringvillage.com/app/doc/?docid=cpx_Mbb49f0b17f8a9b890aM64a51017816328.
     [Google Scholar]
  4. Choi, J., J.Byun, S. J.Seol, and Y.Kim. 2016. “Wavelet‐Based Multicomponent Matching Pursuit Trace Interpolation.” Geophysical Journal International206, no. 3: 1831–1846. https://doi.org/10.1093/gji/ggw246.
     [Google Scholar]
  5. Dosovitskiy, A., L.Beyer, A.Kolesnikov, et al. 2021. “An Image Is Worth 16×16 Words: Transformers for Image Recognition at Scale.” In Paper Read at 9th International Conference on Learning Representations, ICLR 2021, May 3, 2021–May 7, 2021, at Virtual, Online.
  6. Duarte, L. T., D.Donno, R. R.Lopes, and J. M. T.Romano. 2014. “Seismic Signal Processing: Some Recent Advances.” In Paper read at 2014 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2014, May 4, 2014–May 9, 2014, at Florence, Italy.
  7. Fang, W. Q., L. H.Fu, M.Zhang, and Z. M.Li. 2021. “Seismic Data Interpolation Based on U‐Net With Texture Loss.” Geophysics86, no. 1: V41–V54. https://doi.org/10.1190/geo2019‐0615.1.
     [Google Scholar]
  8. Fomel, S.2003. “Seismic Reflection Data Interpolation With Differential Offset and Shot Continuation.” Geophysics68, no. 2: 733–744. https://doi.org/10.1190/1.1567243.
     [Google Scholar]
  9. Kaur, H., N.Pham, and S.Fomel. 2021. “Seismic Data Interpolation Using Deep Learning With Generative Adversarial Networks.” Geophysical Prospecting69, no. 2: 307–326. https://doi.org/10.1111/1365‐2478.13055.
     [Google Scholar]
  10. Li, C., X.Liu, and S.Zu. 2025. “Seismic Data Reconstruction via Least‐Squares Generative Adversarial Networks With Inverse Interpolation.” IEEE Transactions on Geoscience and Remote Sensing63: 1–6. https://doi.org/10.1109/TGRS.2025.3540453.
     [Google Scholar]
  11. Li, Q., L.‐Y.Fu, H.Zhou, W.Wei, and W.Hou. 2019. “Effective Q—Compensated Reverse Time Migration Using New Decoupled Fractional Laplacian Viscoacoustic Wave Equation.” Geophysics84, no. 2: S57–S69. https://doi.org/10.1190/GEO2017‐0748.1.
     [Google Scholar]
  12. Li, X., B.Wu, X.Zhu, and H.Yang. 2022. “Consecutively Missing Seismic Data Interpolation Based on Coordinate Attention Unet.” IEEE Geoscience and Remote Sensing Letters19: 1–5. https://doi.org/10.1109/LGRS.2021.3128511.
     [Google Scholar]
  13. Liu, B., and M. D.Sacchi. 2004. “Minimum Weighted Norm Interpolation of Seismic Records.” Geophysics69, no. 6: 1560–1568. https://doi.org/10.1190/1.1836829.
     [Google Scholar]
  14. Liu, G., X.Chen, J.Du, and K.Wu. 2011. “Nonstationary Autoregression in f‐x Domain for Random Noise Attenuation.” Paper Read at Society of Exploration Geophysicists International Exposition and 81st Annual Meeting 2011, SEG 2011, September 18, 2011–September 23, 2011, at San Antonio, TX, United states.
  15. Liu, G., X.Chen, J.Du, and K.Wu. 2012. “Random Noise Attenuation Using f‐x Regularized Nonstationary Autoregression.” Geophysics77, no. 2: V61–V69. https://doi.org/10.1190/geo2011‐0117.1.
     [Google Scholar]
  16. Liu, G., X.Chen, J.Li, J.Du, and J.Song. 2010. “Seismic Noise Attenuation Using Nonstationary Polynomial Fitting.” In SEG Technical Program Expanded Abstracts. SEG4.
  17. Liu, X., X.Chen, J.Li, X.Zhou, and Y.Chen. 2020. “Facies Identification Based on Multikernel Relevance Vector Machine.” IEEE Transactions on Geoscience and Remote Sensing58, no. 10: 7269–7282. https://doi.org/10.1109/tgrs.2020.2981687.
     [Google Scholar]
  18. Liu, X., F.Lyu, L.Chen, C.Li, S.Zu, and B.Wang. 2024. “Seismic Random Noise Suppression Based on Deep Image Prior and Total Variation.” IEEE Transactions on Geoscience and Remote Sensing62: 1–11. https://doi.org/10.1109/tgrs.2024.3371714.
     [Google Scholar]
  19. Liu, X., G.Shao, Y.Liu, et al. 2022. “Deep Classified Autoencoder for Lithofacies Identification.” IEEE Transactions on Geoscience and Remote Sensing60: 1–14. https://doi.org/10.1109/tgrs.2021.3139931.
     [Google Scholar]
  20. Liu, X. Y., H. L.Zhou, K. K.Guo, C.Li, S. H.Zu, and L. H.Wu. 2023. “Quantitative Characterization of Shale Gas Reservoir Properties Based on BiLSTM With Attention Mechanism.” Geoscience Frontiers14, no. 4: 101567. https://doi.org/10.1016/j.gsf.2023.101567.
     [Google Scholar]
  21. Naghizadeh, M., and M. D.Sacchi. 2007. “Multistep Autoregressive Reconstruction of Seismic Records.” Geophysics72, no. 6: V111–V118. https://doi.org/10.1190/1.2771685.
     [Google Scholar]
  22. Oropeza, V., and M.Sacchi. 2011. “Simultaneous Seismic Data Denoising and Reconstruction via Multichannel Singular Spectrum Analysis: Geophysics.” 76, no. 3: V25–V32. https://doi.org/10.1190/1.3552706.
  23. Pan, X., S.Cao, S.Zu, and F.Gong. 2017. “SVD‐Constrained MWNI With Shaping Theory.” IEEE Geoscience and Remote Sensing Letters14, no. 6: 856–860. https://doi.org/10.1109/LGRS.2017.2683537.
     [Google Scholar]
  24. Park, J., D.Yoon, S. J.Seol, and J.Byun. 2019. “Reconstruction of Seismic Field Data With Convolutional U‐Net Considering the Optimal Training Input Data.” Paper Read at Society of Exploration Geophysicists International Exposition and 89th Annual Meeting, SEG 2019, September 15, 2019–September 20, 2019, at San Antonio, TX, United states.
  25. Qian, F., Z. B.Liu, Y.Wang, S. J.Liao, S. L.Pan, and G. M.Hu. 2022. “DTAE: Deep Tensor Autoencoder for 3‐D Seismic Data Interpolation.” IEEE Transactions on Geoscience and Remote Sensing60: 1–19. https://doi.org/10.1109/tgrs.2021.3075968.
     [Google Scholar]
  26. Ronen, J.1987. “Wave‐Equation Trace Interpolation.” Geophysics52, no. 7: 973–984. https://doi.org/10.1190/1.1442366.
     [Google Scholar]
  27. Shao, J., and Y.Wang. 2022. “Seismic Data Antialiasing Interpolation Using Sparse Radon Transform and Dynamic Mask Function.” Geophysics87, no. 5: V437–V449. https://doi.org/10.1190/geo2021‐0465.1.
     [Google Scholar]
  28. She, Y. Y.2013. “Reduced Rank Vector Generalized Linear Models for Feature Extraction.” Statistics and Its Interface6, no. 2: 197–209.
     [Google Scholar]
  29. Tao, B. C., X. Y.Liu, H. L.Zhou, J. P.Liu, F.Lyu, and Y. C.Lin. 2024. “Porosity Prediction Based on a Structural Modeling Deep‐Learning Method.” Geophysics89, no. 6: M197–M210. https://doi.org/10.1190/geo2024‐0035.1.
     [Google Scholar]
  30. Tao, K., T. Z.Liu, J. Y.Ning, and F. L.Niu. 2014. “Estimating Sedimentary and Crustal Structure Using Wavefield Continuation: Theory, Techniques and Applications.” Geophysical Journal International197, no. 1: 443–457. https://doi.org/10.1093/gji/ggt515.
     [Google Scholar]
  31. Thorson, J. R., and J. F.Claerbout. 1985. “Velocity‐Stack and Slant‐Stack Stochastic Inversion.” Geophysics50, no. 12: 2727–2741. https://doi.org/10.1190/1.1441893.
     [Google Scholar]
  32. Vaswani, A., N.Shazeer, N.Parmar, et al. 2017. “Attention is All You Need.” Paper Read at 31st Annual Conference on Neural Information Processing Systems, NIPS 2017, December 4, 2017–December 9, 2017, at Long Beach, CA, United states.
  33. Wang, B., X.Chen, W.Lu, Z.Guo, and K.Guo. 2016. “Comparison of the POCS and IHT Methods for Seismic Data Interpolation and Denoising.” Paper Read at SEG International Exposition and 86th Annual Meeting, SEG 2016, October 16, 2011–October 21, 2011, at Dallas, TX, United States.
  34. Wang, B., J.Li, and D.Han. 2022. “Iterative Deblending Using MultiResUNet With Multilevel Blending Noise for Training and Transfer Learning.” Geophysics87, no. 3: 1–60. https://doi.org/10.1190/geo2021‐0341.1.
     [Google Scholar]
  35. Wang, B., N.Zhang, and W.Lu. 2019a. “Intelligent Shot Gather Reconstruction Using Residual Learning Networks.” Paper Read at 88th Society of Exploration Geophysicists International Exposition and Annual Meeting, SEG 2018, October 14, 2018–October 19, 2018, at Anaheim, CA, United States.
  36. Wang, B., N.Zhang, W.Lu, and J.Wang. 2019b. “Deep‐Learning‐Based Seismic Data Interpolation: A Preliminary Result.” Geophysics84, no. 1: V11–V20. https://doi.org/10.1190/geo2017‐0495.1.
     [Google Scholar]
  37. Wang, R., M.Li, and L.Wang. 2025. “Super‐Resolution Reconstruction and Prediction of Flow Fields Based on Deep Learning and Modal Decomposition.” Physics of Fluids37, no. 1: 015102. https://doi.org/10.1063/5.0246217.
     [Google Scholar]
  38. Wang, Y. Y., B. F.Wang, N.Tu, and J. H.Geng. 2020. “Seismic Trace Interpolation for Irregularly Spatial Sampled Data Using Convolutional Autoencoder.” Geophysics85, no. 2: V119–V130. https://doi.org/10.1190/geo2018‐0699.1.
     [Google Scholar]
  39. Wang, Y. H.2002. “Seismic Trace Interpolation in the f‐x‐y Domain.” Geophysics67, no. 4: 1232–1239. https://doi.org/10.1190/1.1500385.
     [Google Scholar]
  40. Wang, Z., G.Liu, C.Li, L.Shi, and Z.Wang. 2024. “Random Noise Attenuation of 3D Multicomponent Seismic Data Using a Fast Adaptive Prediction Filter.” Geophysics89, no. 3: V263–V280. https://doi.org/10.1190/geo2023‐0195.1.
     [Google Scholar]
  41. Woo, S., J.Park, J.‐Y.Lee, and I. S.Kweon. 2018. “CBAM: Convolutional Block Attention Module.” In Computer Vision—ECCV 2018: Lecture Notes in Computer Science. Springer Nature. https://www.engineeringvillage.com/app/doc/?docid=cpx_6f3777aa166e496a018M7e0e1017816339.
  42. Xu, Z., D.Sopher, C.Juhlin, L. G.Han, and X. B.Gong. 2018. “Radon‐Domain Interferometric Interpolation for Reconstruction of the Near‐Offset Gap in Marine Seismic Data.” Journal of Applied Geophysics151: 125–141. https://doi.org/10.1016/j.jappgeo.2018.02.012.
     [Google Scholar]
  43. Yu, S. W., J. W.Ma, X. Q.Zhang, and M. D.Sacchi. 2015. “Interpolation and Denoising of High‐Dimensional Seismic Data by Learning a Tight Frame.” Geophysics80, no. 5: V119–V132. https://doi.org/10.1190/geo2014‐0396.1.
     [Google Scholar]
  44. Zhang, H., S.Diao, W.Chen, G.Huang, H.Li, and M.Bai. 2019. “Curvelet Reconstruction of Non‐Uniformly Sampled Seismic Data Using the Linearized Bregman Method.” Geophysical Prospecting67, no. 5: 1201–1218. https://doi.org/10.1111/1365‐2478.12762.
     [Google Scholar]
  45. Zhang, H., H. Q.Zhang, J. H.Zhang, Y. J.Hao, and B. F.Wang. 2020. “An Anti‐Aliasing POCS Interpolation Method for Regularly Undersampled Seismic Data Using Curvelet Transform.” Journal of Applied Geophysics172: 103894. https://doi.org/10.1016/j.jappgeo.2019.103894.
     [Google Scholar]
  46. Zhu, W. Q., S. M.Mousavi, and G. C.Beroza. 2019. “Seismic Signal Denoising and Decomposition Using Deep Neural Networks.” IEEE Transactions on Geoscience and Remote Sensing57, no. 11: 9476–9488. https://doi.org/10.1109/tgrs.2019.2926772.
     [Google Scholar]
/content/journals/10.1111/1365-2478.70137
Loading
A TransUnet Model Integrating Amplitude Consistency Correction and Missing‐Data Masking for Seismic Data Reconstruction
Geophysical Prospecting 74, e70137 (2026); https://doi.org/10.1111/1365-2478.70137
/content/journals/10.1111/1365-2478.70137
/content/journals/10.1111/1365-2478.70137
Loading

Data & Media loading...

  • Article Type: Research Article
Keyword(s): amplitude consistency correction; irregular missing seismic data; masking mechanism; regular missing seismic data; seismic data reconstruction; transformer

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