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

Abstract

ABSTRACT

Multiples are generally considered coherent noise in conventional seismic migration. If they are not appropriately separated or eliminated from the observed reflection data, it can result in significant artefacts of the migration image, which will adversely affect subsequent structural interpretation and reservoir description. Inspired by the state‐of‐the‐art model‐driven deep learning methods, we have proposed a self‐supervised deep‐learning approach for multiple elimination. The proposed method contains two parts. The first one is that we use the conventional multiple prediction approach to predict the initial surface‐related multiple reflections. The second part is to build a multiple‐elimination model based on a deep neural network. In the deep neural network, the input is set as the predicted initial surface‐related multiples from a conventional method and the label is set as the observed reflection data with primaries and multiples. Therefore, the proposed approach is a kind of self‐supervised deep‐learning multiple‐elimination model. The deep neural network component of our proposed approach can be interpreted as a corrector in conventional methods that performs amplitude and phase correction on predicted multiples. Moreover, we combine the advantages of and loss functions and introduce the attention mechanism to improve the inversion efficiency and accuracy of self‐supervised deep networks. Through some experiments with synthesized and field data, we demonstrate that the proposed self‐supervised deep‐learning approach can effectively and efficiently eliminate multiples from the observed data. It excels in both accuracy and efficiency compared to traditional method.

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

Article metrics loading...

/content/journals/10.1111/1365-2478.70128
2026-01-19
2026-02-15

  • From This Site

    /content/journals/10.1111/1365-2478.70128
    dcterms_title,dcterms_subject,pub_keyword
    -contentType:Journal -contentType:Contributor -contentType:Concept -contentType:Institution
    10
    5
Loading full text...

Full text loading...

References

  1. Amundsen, L., L. T.Ikelle, and L. E.Berg. 2001. “Multidimensional Signature Deconvolution and Free‐Surface Multiple Elimination of Marine Multicomponent Ocean‐Bottom Seismic Data.” Geophysics66, no. 5: 1594–1604. https://doi.org/10.1190/1.1486770.
     [Google Scholar]
  2. Bao, P., Y.Shi, W.Wang, J.Xu, and XGuo. 2022. “Surface‐Related and Internal Multiple Elimination Using Deep Learning.” Energies15: 3883. https://doi.org/10.3390/en15113883.
     [Google Scholar]
  3. Berkhout, A. J., and D. JVerschuur. 1997. “Estimation of Multiple Scattering by Iterative Inversion; Part 1, Theoretical Considerations.” Geophysics62, no. 5: 1586–1595. https://doi.org/10.1190/1.1444261.
     [Google Scholar]
  4. Berkhout, A. J., and D. JVerschuur. 2005. “Removal of Internal Multiples with the Common‐Focus‐Point (CFP) Approach: Part 1‐Explanation of the Theory.” Geophysics70, no. 3: V45–V60. https://doi.org/10.1190/1.1925753.
     [Google Scholar]
  5. Brauwers, G., and FFrasincar. 2023. “A General Survey on Attention Mechanisms in Deep Learning.” IEEE Transactions on Knowledge and Data Engineering35, no. 4: 3279–3298. https://doi.org/10.1109/TKDE.2021.3126456.
     [Google Scholar]
  6. Bugge, A. J., A. K.Evensen, J. E.Lie, and E. HNilsen. 2021. “Demonstrating Multiple Attenuation with Model‐Driven Processing Using Neural Networks.” Leading Edge40, no. 11: 831–836. https://doi.org/10.1190/tle40110831.1.
     [Google Scholar]
  7. Cui, H., L.Tian, J.Liu, and NZhang. 2017. “Ordovician Tectonic Activities and Oil and Gas Accu‐Mulation in the Southwest Depression of Tarim Basin.” Oil Geophysical Prospecting52, no. 4: 834–840. https://doi.org/10.7210/(2017)04‐0834‐07.
     [Google Scholar]
  8. Da Costa Filho, C. A., G. A.Meles, and ACurtis. 2017. “Imaging with Marchenko Focusing Functions in Acoustic and Elastic Media.” In 15th International Congress of the Brazilian Geophysical Society. SEG Publications. https://doi.org/10.1190/sbgf2017‐265.
  9. Di, H., C.Li, S.Smith, Z.Li, and AAbubakar. 2021. “Imposing Interpretational Constraints on a Seismic Interpretation CNN.” Geophysics86, no. 3: IM63–IM71. https://doi.org/10.1190/geo2020‐0449.1.
     [Google Scholar]
  10. Di, H., Z.Wang, and G.AlRegib. 2018. “Deep Convolutional Neural Networks for Seismic Salt‐Body Delineation.” In 2018 AAPG Annual Convention & Exhibition. AAPG Publications. https://doi.org/10.1306/70630Di2018.
  11. Donahue, J., Y.Jia, O.Vinyals, et al. 2014. “DeCAF: a Deep Convolutional Activation Feature for Generic Visual Recognition.” In Proceedings of the 31st International Conference on Machine Learning. JMLR.org. https://doi.org/10.48550/arXiv.1310.1531.
     [Google Scholar]
  12. Durall, R., A.Ghanim, N.Ettrich, et al. 2024. “An In‐Depth Study of U‐net for Seismic Data Conditioning: Multiple Removal by Moveout Discrimination.” Geophysics89, no. 1: WA233–WA246. https://doi.org/10.1190/geo2023-0146.1.
     [Google Scholar]
  13. Fabien‐Ouellet, G., and R.Sarkar. 2020. “Seismic Velocity Estimation: a Deep Recurrent Neural‐Network Approach.” Geophysics85, no. 1: U21–U29. https://doi.org/10.1190/geo2018‐0786.1.
     [Google Scholar]
  14. Fernandez, M., N.Ettrich, M.Delescluse, A.Rabaute, and J.Keuper. 2023. “Seismic Demultiple with Deep Learning.” In 84th EAGE Annual Conference & Exhibition. European Association of Geoscientists & Engineers. https://doi.org/10.3997/2214‐4609.2023101170.
  15. Foster, D. J., and C. CMosher. 1992. “Suppression of Multiple Reflections Using the Radon Transform.” Geophysics57, no. 3: 386–395. https://doi.org/10.1190/1.1443253.
     [Google Scholar]
  16. Girshick, R.2015. “Fast R‐CNN.” In IEEE International Conference on Computer Vision (ICCV). IEEE. https://doi.org/10.1109/ICCV.2015.169.
  17. Guitton, A., and D. JVerschuur. 2004. “Adaptive Subtraction of Multiples Using L1‐Norm.” Geophysical Prospecting52, no. 1: 27–38.
     [Google Scholar]
  18. Hampson, D.1986. “Inverse Velocity Stacking for Multiple Elimination.” Journal of the Canadian Society of Exploration Geophysicists22, no. 1: 44–55. https://doi.org/10.1190/1.1893060.
     [Google Scholar]
  19. He, K., X.Zhang, S.Ren, and JSun. 2016. “Deep Residual Learning for Image Recognition.” In 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE. https://doi.org/10.1109/CVPR.2016.90.
  20. Hinton, G. E., and R. R.Salakhutdinov. 2006. “Reducing the Dimensionality of Data with Neural Networks.” Science313: 504–507. https://doi.org/10.1126/science.1127647.
     [Google Scholar]
  21. Jia, Y., and J.Ma. 2017. “What Can Machine Learning Do for Seismic Data Processing? An Interpolation Application.” Geophysics82, no. 3: V163–V177. https://doi.org/10.1190/geo2016‐0300.1.
     [Google Scholar]
  22. Kingma, D., and JBa. 2014. “Adam: a Method for Stochastic Optimization.” International Conference on Learning Representations, San Diego, CA, USA. https://doi.org/10.48550/arXiv.1412.6980.
     [Google Scholar]
  23. Li, X., and T.Hu. 2009. “Surface‐Related Multiple Removal with Inverse Scattering Series Method.” Chines Journal of Geophysics (in Chinese)52, no. 6: 1633–1640. https://doi.org/10.3969/j.issn.0001‐5733.2009.06.026.
     [Google Scholar]
  24. Lokshtanov, D.1999. “Multiple Suppression by Data‐Consistent Deconvolution.” Leading Edge18, no. 1: 115–119. https://doi.org/10.1190/1.1820122.
     [Google Scholar]
  25. Majdanski, M., C.Kostov, E.Kragh, I.Moore, M.Thompson, and JMispel. 2011. “Attenuation of Free‐Surface Multiples by Up/Down Deconvolution for Marine Towed‐Streamer Data.” Geophysics76, no. 6: V129–V138. https://doi.org/10.1190/GEO2010‐0337.1.
     [Google Scholar]
  26. Meles, C. A., K.Löer, M.Ravasil, A.Curtis, and C. ADa Costa Filho. 2015. “Internal Multiple Prediction and Removal Using Marchenko Autofocusing and Seismic Interferometry.” Geophysics80, no. 1: A7–A11. https://doi.org/10.1190/GEO2014‐0408.1.
     [Google Scholar]
  27. Mnih, V., N.Heess, and AGraves. 2014. “Recurrent Models of Visual Attention.” In NIPS'14: Proceedings of the 28th International Conference on Neural Information Processing Systems. Association for Computing Machinery. https://doi.org/10.48550/arXiv.1406.6247.
  28. Qu, Q., Y.Tang, H.Wang, and WLan. 2000. “The Petroleum System and Objective Interval for Exploration of Cambrian in Southwest Depression of Tarim Basin.” Xing Jiang Petroleum Geology (in Chinese)21, no. 2: 101–104.
     [Google Scholar]
  29. Qu, S., E.Verschuur, D.Zhang, and YChen. 2021. “Training Deep Networks with Only Synthetic Data: Deep‐Learning‐Based Near‐Offset Reconstruction for Closed‐Loop Surface‐Related Multiple Estimation on Shallow‐Water Field Data.” Geophysics86, no. 3: A39–A43. https://doi.org/10.1190/geo2020‐0723.1.
     [Google Scholar]
  30. Robert, S., N.Philippe, A.Hussain, and N.AlBinHassan. 2022. “Robust Deep Learning‐Based Seismic Inversion Workflow Using Temporal Convolutional Networks.” Interpretation10, no. 2: SC41–SC55. https://doi.org/10.1190/INT‐2021‐0142.1.
     [Google Scholar]
  31. Ronneberger, O., P.Fischer, and T.Brox. 2015. “U‐Net: Convolutional Networks for Biomedical Image Segmentation.” In Medical Image Computing and Computer‐Assisted Intervention (MICCAI). Springer. https://doi.org/10.48550/arXiv.1505.04597.
  32. Ross, C. P., and D. MCole. 2017. “A Comparison of Popular Neural Network Facies‐Classification Schemes.” Leading Edge36, no. 4: 340–349. https://doi.org/10.1190/tle36040340.1.
     [Google Scholar]
  33. Russakovsky, O., J.Deng, H.Su, et al. 2015. “Imagenet Large Scale Visual Recognition Challenge.” International Journal of Computer Vision115: 211–252. https://doi.org/10.1007/s11263‐015‐0816‐y.
     [Google Scholar]
  34. Siahkoohi, A., D. J.Verschuur, and F. J.Herrmann. 2019. “Surface‐Related Multiple Elimination with Deep Learning.” In SEG Technical Program Expanded Abstracts. SEG Publications. https://doi.org/10.1190/segam2019‐3216723.1.
  35. Singh, S., R.Snieder, J.Behura, J.Van Der Neut, K.Wapenaar, and E.Slob. 2015. “Marchenko Imaging: Imaging with Primaries, Internal Multiples, and Free‐Surface Multiples.” Geophysics80, no. 5: S165–S174. https://doi.org/10.1190/segam2014‐1593.1.
     [Google Scholar]
  36. Song, H., W.Mao, and H.Tang. 2021. “Applicatio of Deep Neural Networks for Multiples Attenuation.” Chines Journal of Geophysics (in Chinese)64, no. 8: 2795–2808. https://doi.org/10.6038/cjg2021O0369.
     [Google Scholar]
  37. Soydaner, D.2022. “Attention Mechanism in Neural Networks: Where It Comes and Where It Goes.” Neural Computing and Applications34, no. 6: 1–22. https://doi.org/10.1007/s00521‐022‐07366‐3.
     [Google Scholar]
  38. Sun, W., Z.Li, Y.Qu, and Z.Li. 2019. “Multiple Attenuation Using λ‐f Domain High‐Order and High‐Resolution Radon Transform Based on SL0 Norm.” Applied Geophysics16, no. 4: 473–482. https://doi.org/10.1007/s11770‐019‐0795‐9.
     [Google Scholar]
  39. Taner, M. T.1980. “Long Period Sea‐Floor Multiples and Their Suppression.” Geophysical Prospecting28, no. 1: 30–48. https://doi.org/10.1111/j.1365‐2478.1980.tb01209.x.
     [Google Scholar]
  40. van der Neut, J., I.Vasconcelos, and K.Wapenaar. 2015. “On Green's Function Retrieval by Iterative Substitution of the Coupled Marchenko Equations.” Geophysical Journal International203, no. 2: 792–813. https://doi.org/10.1093/gji/ggv330.
     [Google Scholar]
  41. Verschuur, D. J., and A. J.Berkhout. 1997. “Estimation of Multiple Scattering by Iterative Inversion, Part II: Practical Aspects and Examples.” Geophysics62, no. 5: 1596–1611. https://doi.org/10.1190/1.1444262.
     [Google Scholar]
  42. Verschuur, D. J., A. J.Berkhout, and C.Wapenaar. 1992. “Adaptive Surface‐Related Multiple Elimination.” Geophysics57, no. 9: 1166–1177. https://doi.org/10.1190/1.1443330.
     [Google Scholar]
  43. Vrolijk, J. W., and G.Blacquière. 2021. “Source Deghosting of Coarsely‐Sampled Common‐Receiver Data Using a Convolutional Neural Network.” Geophysics86, no. 3: V185–V196. https://doi.org/10.1190/geo2020‐0186.1.
     [Google Scholar]
  44. Wang, K., T.Hu, X.Liu, S.Wang, and J.Wei. 2021. “Suppressing Seismic Multiples Based on the Deep Neural Network Method.” Chines Journal of Geophysics (in Chinese)64, no. 11: 4196–4214. https://doi.org/10.6038/cjg2021O0517.
     [Google Scholar]
  45. Wang, R., and L.Guo. 2020. “The Distribution of Combustible Ice and the Status of Exploitation.” IOP Conference Series: Earth and Environmental Science467: 012069. https://doi.org/10.1088/1755‐1315/467/1/012069.
     [Google Scholar]
  46. Wapenaar, K., J.Brackenhoff, M.Dukalski, and G.Meles. 2021. “Marchenko Redatuming, Imaging and Multiple Elimination, and Their Mutual Relations.” Geophysics86, no. 5: WC117–WC140. https://doi.org/10.1190/geo2020‐0854.1.
     [Google Scholar]
  47. Wapenaar, K., F.Broggini, and R.Snieder. 2012. “Creating a Virtual Source inside a Medium from Reflection Data: Heuristic Derivation and Stationary Phase Analysis.” Geophysical Journal International190: 1020–1024. https://doi.org/10.1111/j.1365‐246X.2012.05551.x.
     [Google Scholar]
  48. Weglein, A. B., G. F.Araújo, P. M.Carvalho, and R. H.Stolt. 1997. “An Inverse‐Scattering Series Method for Attenuating Multiples in Seismic Reflection Data.” Geophysics62, no. 6: 1975–1989. https://doi.org/10.1190/1.1444298.
     [Google Scholar]
  49. Wu, X., Z.Geng, Y.Shi, N.Pham, S.Fomel, and G.Caumon. 2020. “Building Realistic Structure Models to Train Convolutional Neural Networks for Seismic Structural Interpretation.” Geophysics85, no. 4: WA27–WA39. https://doi.org/10.1190/geo2019‐0375.1.
     [Google Scholar]
  50. Yang, L., W.Chen, H.Wang, and Y.Chen. 2021. “Deep Learning Seismic Random Noise Attenuation via Improved Residual Convolutional Neural Network.” IEEE Transactions on Geoscience and Remote Sensing59, no. 9: 7968–7981. https://doi.org/10.1109/TGRS.2021.3053399.
     [Google Scholar]
  51. Yu, S., J.Ma, and W.Wang. 2019. “Deep Learning for Denoising.” Geophysics84, no. 6: V333–V350. https://doi.org/10.1190/GEO2018‐0668.1.
     [Google Scholar]
  52. Yuan, P., S.Wang, W.Hu, X.Wu, J.Chen, and H. V.Nguyen. 2020. “A Robust First‐Arrival Picking Workflow Using Convolutional and Recurrent Neural Networks.” Geophysics85, no. 5: U109–U119. https://doi.org/10.1190/geo2019‐0437.1 .
     [Google Scholar]
  53. Zeng, Y., K.Jiang, and J.Chen. 2018. “Automatic Seismic Salt Interpretation with Deep Convolutional Neural Networks.” In The 3rd International Conference on Information System and Data Mining. Association for Computing Machinery. https://doi.org/10.1145/3325917.3325926.
  54. Zhang, C., C.Frogner, M.Araya‐Polo, and D.Hohl. 2014. “Machine‐Learning Based Automated Fault Detection in Seismic Traces.” In 76th Annual International Conference and Exhibition. European Association of Geoscientists & Engineers. https://doi.org/10.3997/2214‐4609.20141500.
  55. Zhang, L., E.Han, L.Zhu, et al. 2015. “Characteristics of Evaporites Sedimentary Cycles and Its Controlling Factors of Paleocene Aertashi Formation in the Southwestern Tarim Depression.” Acta Geologica Sinica89, no. 11: 2161–2170. https://doi.org/10.19762/j.cnki.dizhixuebao.2015.11.027.
     [Google Scholar]
  56. Zhang, L., and E.Slob. 2020. “A Field Data Example of Marchenko Multiple Elimination.” Geophysics85, no. 2: S65–S70. https://doi.org/10.1190/GEO2019‐0327.1.
     [Google Scholar]
  57. Zhang, W., and J.Gao. 2022. “Deep‐Learning Full‐Waveform Inversion Using Seismic Migration Images.” IEEE Transactions on Geoscience and Remote Sensing60: 5901818. https://doi.org/10.1109/TGRS.2021.3062688.
     [Google Scholar]
  58. Zhang, W., M.Ravasi, J.Gao, and Y.Shi. 2024. “Deep‐Unrolling Architecture for Image‐Domain Least‐Squares Migratio.” Geophysics89, no. 3: S215–S234. https://doi.org/10.1190/geo2023‐0428.1.
     [Google Scholar]
  59. Zhao, Q., X.Cai, C.Chen, L.Lv, and M.Chen. 2017. “Commented Content Classification with Deep Neural Network Based on Attention Mechanism.” In IEEE 2nd Advanced Information Technology, Electronic and Automation Control Conference (IAEAC). IEEE. https://doi.org/10.1109/IAEAC.2017.8054369.
  60. Zillich, M., S.Frintrop, F.Pirri, E.Potapova, and M.Vincze. 2014. “Workshop on Attention Models in Robotics: Visual Systems for Better HRI.” In 9th ACM/IEEE International Conference on Human‐Robot Interaction (HRI). Association for Computing Machinery. https://doi.org/10.1145/2559636.2563723.
/content/journals/10.1111/1365-2478.70128
Loading
Multiple Elimination Using Model‐Driven Self‐Supervised Learning With an Attention Mechanism
Geophysical Prospecting 74, e70128 (2026); https://doi.org/10.1111/1365-2478.70128
/content/journals/10.1111/1365-2478.70128
/content/journals/10.1111/1365-2478.70128
Loading

Data & Media loading...

  • Article Type: Research Article
Keyword(s): attention mechanism; model driven; multiple elimination; self‐supervised deep‐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