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

Abstract

ABSTRACT

High‐resolution seismic data are essential for interpreting thin‐layered stratigraphy and subtle structures within hardrock media, as this information can lead to better exploration decisions in the mining sector. Conventional resolution enhancement techniques, such as spectral broadening and supervised deep‐learning techniques, often rely on oversimplified assumptions or require high‐resolution training labels. These limitations restrict their applicability in real seismic data processing, especially for hardrock seismic data, which are typically characterized by high velocities, strong heterogeneity and short reflector continuity due to complex emplacement contacts and geological settings. We propose an unsupervised seismic resolution enhancement framework that integrates physics‐guided and attention‐based mechanisms. The framework is designed to address the progressive loss of high‐frequency information in seismic exploration and the limitations of conventional resolution enhancement methods, which struggle to balance imaging fidelity with geological interpretability. The proposed network incorporates coordinate attention blocks and the lightweight Vision Transformer, enabling more effective capture of spatial dependencies and long‐range significant features in complex geological settings. Specifically, our approach utilizes a physics‐constrained deconvolutional loss function, where the predicted reflectivity is regularized by an adaptive sparsity prior and convolved with a wavelet to synthesize seismic traces that are consistent with the observed data. In addition, a robust Charbonnier penalty ensures stable physical fitting, while anisotropic total variation regularization improves lateral continuity. Following this design, the model achieves end‐to‐end recovery of high‐resolution seismic information without requiring high‐resolution labels, thereby explicitly embedding physical constraints into the learning process. Testing results on synthetic and field datasets from two different regions demonstrate that the proposed method significantly enhances vertical resolution, reflector sharpness and lateral continuity, enabling more precise delineation of subtle stratigraphic features within the target intervals. Compared with spectral enhancement and conventional deep‐learning methods, our approach achieves higher seismic reconstruction fidelity and more interpretable reflectivity, providing an option that combines robustness with interpretability for high‐resolution imaging in complex geological conditions.

© 2026 European Association of Geoscientists & Engineers. © 2026 The Author(s). Geophysical Prospecting published by John Wiley & Sons Ltd on behalf of European Association of Geoscientists & Engineers.
Loading

Article metrics loading...

/content/journals/10.1111/1365-2478.70123
2026-01-04
2026-02-15

  • From This Site

    /content/journals/10.1111/1365-2478.70123
    dcterms_title,dcterms_subject,pub_keyword
    -contentType:Journal -contentType:Contributor -contentType:Concept -contentType:Institution
    10
    5
Loading full text...

Full text loading...

/deliver/fulltext/gpr/74/1/gpr70123.html?itemId=/content/journals/10.1111/1365-2478.70123&mimeType=html&fmt=ahah

References

  1. Ahadi, A., and M. A.Riahi. 2013. “Application of Gabor Deconvolution to Zero‐Offset VSP Data.” Geophysics78, no. 2: D85–D91.
     [Google Scholar]
  2. Al‐Mekhlafi, H., and S.Liu. 2024. “Single Image Super‐Resolution: A Comprehensive Review and Recent Insight.” Frontiers of Computer Science18, no. 1: 181702.
     [Google Scholar]
  3. Alaei, N., A. R.Kahoo, A. K.Rouhani, and M.Soleimani. 2019. “Seismic Resolution Enhancement Using Scale Transform in the Time‐Frequency Domain.” Geophysics83, no. 5: V305–V314.
     [Google Scholar]
  4. Chai, X., T.Yang, H.Gu, G.Tang, W.Cao, and Y.Wang. 2023. “Geophysics‐Steered Self‐Supervised Learning for Deconvolution.” Geophysical Journal International234: 40–55.
     [Google Scholar]
  5. Chen, G., Y.Liu, M.Zhang, Y.Sun, and H.Zhang. 2025. “Unsupervised Seismic Reconstruction via Deep Learning With One‐Dimensional Signal Representation.” Computers and Geosciences200: 105916.
     [Google Scholar]
  6. Chen, Y2019. “Multi‐Channel Quality Factor Q Estimation.” Geophysical Journal International218: 655–665.
     [Google Scholar]
  7. Chen, Y., M.Bai, and Y.Chen. 2019. “Obtaining Free USArray Data by Multi‐Dimensional Seismic Reconstruction.” Nature Communications10: 4434.
     [Google Scholar]
  8. Cheng, S., H.Zhang, and T.Alkhalifah. 2025. “Self‐Supervised Seismic Resolution Enhancement.” IEEE Transactions on Geoscience and Remote Sensing63: 5904115.
     [Google Scholar]
  9. Dosovitskiy, A., L.Beyer, A.Kolesnikov, et al. 2020. “An Image is Worth 16×$\times$16 Words: Transformers for Image Recognition at Scale.” Preprint, arXiv, June 3. https://doi.org/10.48550/arXiv.2010.11929.
  10. Du, X., G.Li, M.Zhang, H.Li, W.Yang, and W.Wang. 2018. “Multichannel Band‐Controlled Deconvolution Based on a Data‐Driven Structural Regularization.” Geophysics83: R401–R411.
     [Google Scholar]
  11. Gao, Y., J.Zhang, H.Li, and G.Li. 2022. “Incorporating Structural Constraint Into the Machine Learning High‐Resolution Seismic Reconstruction.” IEEE Transactions on Geoscience and Remote Sensing60: 5912712.
     [Google Scholar]
  12. Gao, Y., D.Zhao, T.Li, G.Li, and S.Guo. 2023. “Deep Learning Vertical Resolution Enhancement Considering Features of Seismic Data.” IEEE Transactions on Geoscience and Remote Sensing61: 5900913.
     [Google Scholar]
  13. Gholami, A., and M. D.Sacchi. 2013. “Fast 3D Blind Seismic Deconvolution via Constrained Total Variation and GCV.” SIAM Journal on Imaging Sciences6: 2350–2369.
     [Google Scholar]
  14. Grasmair, M., and F.Lenzen. 2010. “Anisotropic Total Variation Filtering.” Applied Mathematics and Optimization62: 323–339.
     [Google Scholar]
  15. Gyger, L., A.Malehmir, M.Manzi, et al. 2024. “Broadband Seismic Data Acquisition and Processing of Iron Oxide Deposits in Blötberget, Sweden.” Geophysical Prospecting73: 80–95. https://doi.org/10.1111/1365–2478.13648.
     [Google Scholar]
  16. Hou, Q., D.Zhou, and J.Feng. 2021. “Coordinate Attention for Efficient Mobile Network Design.” Preprint, arXiv, March 4. https://doi.org/10.48550/arXiv.2103.02907.
  17. Kingma, D. P., and J.Ba. 2014. “Adam: A Method for Stochastic Optimization.” Preprint, arXiv, December 22. https://doi.org/10.48550/arXiv.1412.6980.
  18. Lai, W., J.Huang, N.Ahuja, and M.Yang. 2019. “Fast and Accurate Image Super‐Resolution with Deep Laplacian Pyramid Networks.” IEEE Transactions on Pattern Analysis and Machine Intelligence41: 2599–2613.
     [Google Scholar]
  19. LeCun, Y., Y.Bengio, and G.Hinton. 2015. “Deep Learning.” Nature521: 436–444.
     [Google Scholar]
  20. Li, C., S.Fomel, Y.Chen, R.Dommisse, and A.Savvaidis. 2025. “FaultVitNet: A Vision Transformer Assisted Network for 3D Fault Segmentation.” Journal of Geophysical Research: Machine Learning and Computation2: e2024JH000488.
     [Google Scholar]
  21. Li, C., and G.Liu. 2022. “Warped Mapping‐Based Blind Deconvolution for Resolution Improvement.” Geophysical Prospecting70: 677–701.
     [Google Scholar]
  22. Li, C., G.Liu, Z.Wang, Z.Li, S.Fomel, and Y.Chen. 2025. “Simultaneous Off‐the‐Grid Deblending and Data Reconstruction via Unsupervised Deep Learning.” IEEE Transactions on Geoscience and Remote Sensing63: 5909311.
     [Google Scholar]
  23. Li, C., G.Liu, Z.Wang, L.Shi, and Q.Wu. 2023. “Robust Q‐Compensated Multidimensional Impedance Inversion Using Seislet‐Domain Shaping Regularization.” Geophysics89: 1–82.
     [Google Scholar]
  24. Li, C., G.Liu, Z.Wang, Q.Wu, and L.Shi. 2023. “Multichannel Joint Resolution Enhancement for Nonstationary Prestack Data With Adaptive Structure Regularization.” Geophysics88: V361–V370.
     [Google Scholar]
  25. Li, C., O. M.Saad, and Y.Chen. 2025. “Unsupervised Deep Learning for Off‐the‐Grid Seismic Reconstruction and Denoising.” Geophysics90: V241–V254.
     [Google Scholar]
  26. Li, J., S.Wang, D.Yang, G.Tang, and Y.Chen. 2018. “Subsurface Attenuation Estimation Using a Novel Hybrid Method Based on FWE Function and Power Spectrum.” Exploration Geophysics49: 220–230.
     [Google Scholar]
  27. Liang, C., J.Castagna, and R. Z.Torres. 2017. “Tutorial: Spectral Bandwidth Extension‐Invention Versus Harmonic Extrapolation.” Geophysics82: W1–W16.
     [Google Scholar]
  28. Liu, D., Y.He, X.Wang et al. 2025. “From Shallow to Deep: Enhancing Seismic Resolution With Weak Supervision.” Geophysics90: V223–V239.
     [Google Scholar]
  29. Liu, D., W.Niu, X.Wang, M. D.Sacchi, W.Chen, and C.Wang. 2023. “Improving Vertical Resolution of Vintage Seismic Data by a Weakly Supervised Method Based on Cycle Generative Adversarial Network.” Geophysics88: V445–V458.
     [Google Scholar]
  30. Liu, G., C.Li, Y.Rao, and X.Chen. 2020. “Oriented Prestack Inverse Q Filtering for Resolution Enhancements of Seismic Data.” Geophysical Journal International223: 488–501.
     [Google Scholar]
  31. Malehmir, A., G.Maries, E.Backstrom, M.Schon, and P.Marsden. 2017. “Developing Cost‐Effective Seismic Mineral Exploration Methods Using a Landstreamer and a Drophammer.” Scientific Reports7: 10325.
     [Google Scholar]
  32. Malehmir, A., M.Markovic, P.Marsden et al. 2021. “Sparse 3D Reflection Seismic Survey for Deep‐Targeting Iron Oxide Deposits and Their Host Rocks, Ludvika Mines, Sweden.” Solid Earth12: 483–502.
     [Google Scholar]
  33. Malehmir, A., A.Tryggvason, C.Wijns et al. 2018. “Why 3D Seismic Data Are an Asset for Exploration and Mine Planning? Velocity Tomography of Weakness Zones in the Kevitsa Ni‐Cu‐PGE Mine, Northern Finland.” Geophysics83: B33–B46.
     [Google Scholar]
  34. Markovic, M., R.Malehmir, and A.Malehmir. 2022. “Diffraction Pattern Recognition Using Deep Semantic Segmentation.” Near Surface Geophysics20: 507–518.
     [Google Scholar]
  35. Markovic, M., G.Maries, A.Malehmir et al. 2020. “Deep Reflection Seismic Imaging of Iron‐Oxide Deposits in the Ludvika Mining Area of Central Sweden.” Geophysical Prospecting68: 7–23.
     [Google Scholar]
  36. Martin, G. S., R.Wiley, and K. J.Marfurt. 2006. “Anisotropic Total Variation Filtering.” The Leading Edge25: 113–224.
     [Google Scholar]
  37. Nose‐Filho, K., A. K.Takahata, R.Lopes, and J. M. T.Romano. 2016. “A Fast Algorithm for Sparse Multichannel Blind Deconvolution.” Geophysics81: V7–V16.
     [Google Scholar]
  38. Oktay, O., J.Schlemper, L. L.Folgoc, et al. 2018. “Attention U‐Net: Learning Where to Look for the Pancreas.” Preprint, arXiv, April 11. https://doi.org/10.48550/arXiv.1804.03999.
  39. Saad, O. M., I.Helmy, and Y.Chen. 2024. “Unsupervised Deep‐Learning Framework for 5D Seismic Denoising and Interpolation.” Geophysics89: V319–V330.
     [Google Scholar]
  40. Sajid, M., and A. R.Ghazali. 2018. “Nonstationary Differential Resolution: An Algorithm to Improve Seismic Resolution.” Geophysics83: V149–V156.
     [Google Scholar]
  41. Shi, S., Y.Qi, W.Chang, L.Li, X.Yao, and J.Shi. 2023. “Acoustic Impedance Inversion in Coal Strata Using the Priori Constraint‐Based TCN‐BiGRU Method.” Advance in Geo‐Energy Research9: 13–24.
     [Google Scholar]
  42. Wang, D., Y.Tian, K.Zhang et al. 2024. “Anti‐Noise Full‐Frequency Expansion for Seismic Data With Compressed Sensing.” IEEE Transactions on Geoscience and Remote Sensing62: 1–16.
     [Google Scholar]
  43. Wang, H., G.Huang, W.Chen, and Y.Chen. 2021. “Q‐Compensated Denoising of Seismic Data.” IEEE Transactions on Geoscience and Remote Sensing59: 3580–3587.
     [Google Scholar]
  44. Wang, Y., X.Ma, H.Zhou, and Y.Chen. 2018. “L1‐2 Minimization for Exact and Stable Seismic Attenuation Compensation.” Geophysical Journal International213: 1629–1646.
     [Google Scholar]
  45. Wang, Y., J.Xu, Z.Zhao, Y.Gao, and H.Zhang. 2024. “Structurally‐Constrained Unsupervised Deep Learning for Seismic High‐Resolution Reconstruction.” IEEE Transactions on Geoscience and Remote Sensing62: 5901115.
     [Google Scholar]
  46. Wang, Y., G.Zhang, H.Li, W.Yang, and W.Wang. 2022. “The High‐Resolution Seismic Deconvolution Method Based on Joint Sparse Representation Using Logging‐Seismic Data.” Geophysical Prospecting70: 1313–1326.
     [Google Scholar]
  47. Wang, Y., H.Zhou, H.Chen, and Y.Chen. 2018. “Adaptive Stabilization for Q‐Compensated Reverse Time Migration.” Geophysics83: S15–S32.
     [Google Scholar]
  48. Wang, Y., H.Zhou, Q.Zhang, and Y.Chen. 2019. “Q‐Compensated Viscoelastic Reverse Time Migration Using Mode‐Dependent Adaptive Stabilization Scheme.” Geophysics84: S301–S315.
     [Google Scholar]
  49. Wang, Y., H.Zhou, Q.Zhang, P.Zhao, X.Yu, and Y.Chen. 2019. “CuQ‐RTM: A CUDA‐Based Code Package for Stable and Efficient Q‐Compensated Reverse Time Migration.” Geophysics84: F1–F15.
     [Google Scholar]
  50. Wu, X., L.Liang, Y.Shi, and S.Fomel. 2019. “FaultSeg3D: Using Synthetic Data Sets to Train an End‐to‐End Convolutional Neural Network for 3D Seismic Fault Segmentation.” Geophysics84: IM35–IM45.
     [Google Scholar]
  51. Xu, S., Y.Liu, Z.Zou, Y.Liu, X.Yao, and J.Shi. 2025. “Borehole Full‐Waveform Inversion of Monopole Logging in Slow Formations: Insights for Shear‐Wave Velocity Profiling.” Advance in Geo‐Energy Research17: 82–90.
     [Google Scholar]
  52. Yang, L., S.Fomel, S.Wang et al. 2023. “Denoising of Distributed Acoustic Sensing Data Using Supervised Deep Learning.” Geophysics88: WA91–WA104.
     [Google Scholar]
  53. Yang, L., M.Markovic, and A.Malehmir. 2025. “Enhanced Hardrock Seismic Imaging Through Multi‐Scale Information‐Guided Unsupervised Learning.” Journal of Geophysical Research: Machine Learning and Computation2: e2025JH000627.
     [Google Scholar]
  54. Zhang, H., Y.Liu, Y.Sun, and G.Chen. 2024. “SeisResoDiff: Seismic Resolution Enhancement Based on a Diffusion Model.” Petroleum Science21: 3166–3188.
     [Google Scholar]
  55. Zhang, R.2019. “Making Convolutional Networks Shift‐Invariant Again.” Preprint, arXiv, June 9. https://doi.org/10.48550/arXiv.1904.11486.
  56. Zhang, R., and J.Castagna. 2011. “Seismic Sparse‐Layer Reflectivity Inversion Using Basis Pursuit Decomposition.” Geophysics76: R147–R158.
     [Google Scholar]
/content/journals/10.1111/1365-2478.70123
Loading
Unsupervised Physics‐Guided Deconvolution for High‐Resolution Hardrock Seismic Imaging
Geophysical Prospecting 74, e70123 (2026); https://doi.org/10.1111/1365-2478.70123
/content/journals/10.1111/1365-2478.70123
/content/journals/10.1111/1365-2478.70123
Loading

Data & Media loading...

  • Article Type: Research Article
Keyword(s): attention mechanism; deep‐learning; physics‐guided deconvolution; resolution enhancement; unsupervised learning

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