1887
Volume 72, Issue 7
  • E-ISSN: 1365-2478
PDF

Abstract

Abstract

Deghosting of marine seismic data is an important and challenging step in the seismic processing flow. We describe a novel approach to train a supervised convolutional neural network to perform joint source and receiver deghosting of single‐component (hydrophone) data. The training dataset is generated by demigration of stacked depth migrated images into shot gathers with and without ghosts using the actual source and receiver locations from a real survey. To create demigrated data with ghosts, we need an estimate of the depth of the sources and receivers and the reflectivity of the sea surface. In the training process, we systematically perturbed these parameters to create variability in the ghost timing and amplitude and show that this makes the convolutional neural network more robust to variability in source/receiver depth, swells and sea surface reflectivity. We tested the new method on the Marmousi synthetic data and real North Sea field data and show that, in some respects, it performs better than a standard deterministic deghosting method based on least‐squares inversion in the domain. On the synthetic data, we also demonstrate the robustness of the new method to variations in swells and sea‐surface reflectivity.

© 2024 European Association of Geoscientists & Engineers. © 2022 The Authors. Geophysical Prospecting published by John Wiley & Sons Ltd on behalf of European Association of Geoscientists & Engineers.
Loading

Article metrics loading...

/content/journals/10.1111/1365-2478.13253
2024-08-23
2025-11-11

  • From This Site

    /content/journals/10.1111/1365-2478.13253
    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/72/7/gpr13253.html?itemId=/content/journals/10.1111/1365-2478.13253&mimeType=html&fmt=ahah

References

  1. Almuteri, K. & Sava, P. (2021) A convolutional neural network approach for ghost removal seismic deghosting using CNNs. In: First International Meeting for Applied Geoscience & Energy Expanded Abstracts, Society of Exploration Geophysicists, pp. 2550–2554.
     [Google Scholar]
  2. Amundsen, L. & Zhou, H. (2013) Low‐frequency seismic deghosting. Geophysics, 78, WA15–WA20.
     [Google Scholar]
  3. Amundsen, L., Weglein, A.B. & Reitan, A. (2013a) On seismic deghosting using integral representation for the wave equation: Use of Green's functions with Neumann or Dirichlet boundary conditions. Geophysics, 78, T89–T98.
     [Google Scholar]
  4. Amundsen, L., Zhou, H., Reitan, A. & Weglein, A.B. (2013b) On seismic deghosting by spatial deconvolution. Geophysics, 78, 267–271.
     [Google Scholar]
  5. Asgedom, E.G., Cecconello, E., Orji, O.C. & Söllner, W. (2017) Rough sea surface reflection coefficient estimation and its implication on hydrophone‐only pre‐stack Deghosting. In: 79th EAGE Conference and Exhibition 2017. EAGE, pp. 12–15.
     [Google Scholar]
  6. Aytun, K. (1999) The footsteps of the receiver ghost in the f‐k domain. Geophysics, 64, 1618–1626.
     [Google Scholar]
  7. Bearnth, R.E. & Moore, N.A. (1989) Air gun‐slant cable seismic results in the Gulf of Mexico. In: 1989 SEG Annual Meeting. SEG, pp. 649–652.
     [Google Scholar]
  8. Blacquière, G. & Sertlek, H.Ö. (2019) Modeling and assessing the effects of the sea surface, from being flat to being rough and dynamic. Geophysics, 84, T13–T27.
     [Google Scholar]
  9. Brittan, J., Martin, T., Bekara, M. & Koch, K. (2011) 3D shallow water demultiple – extending the concept. First Break, 29, 97–101.
     [Google Scholar]
  10. Carlson, D., Long, A., Söllner, W., Tabti, H., Tenghamn, R. & Lunde, N. (2007) Increased resolution and penetration from a towed dual‐sensor streamer. First Break, 25, 71–77.
     [Google Scholar]
  11. CGG . (2020) NVG 3D seismic. Available at https://www.cgg.com/multi‐client‐data/multi‐client‐seismic/northern‐viking‐graben (Accessed: 01 August 2022).
  12. Chang, H., Solano, M., VanDyke, J.P., McMechan, G.A. & Epili, D. (1996) 3‐D prestack Kirchhoff depth migration: From prototype to production in a MPP environment. Geophysics, 63, 546–556.
     [Google Scholar]
  13. Cunha, A., Pochet, A., Lopes, H. & Gattass, M. (2020) Seismic fault detection in real data using transfer learning from a convolutional neural network pre‐trained with synthetic seismic data. Computers and Geosciences, 135, 1–9.
     [Google Scholar]
  14. Dumoulin, V. & Visin, F. (2016) A guide to convolution arithmetic for deep learning [preprint]. ArXiv, 1603.07285.
  15. Fang, W., Fu, L., Zhang, M. & Li, Z. (2021) Seismic data interpolation based on U‐net with texture loss. Geophysics, 86, V41–V54.
     [Google Scholar]
  16. Goodfellow, I., Bengio, Y. & Courville, A. (2016) Deep Learning. MIT Press.
     [Google Scholar]
  17. Greiner, T.L., Kolbjørnsen, O., Lie, J.E., Nilsen, E.H., Evensen, A.K. & Gelius, L. (2019) Cross‐streamer wavefield interpolation using deep convolutional neural network. In: SEG Technical Program Expanded Abstracts 2019. SEG, pp. 2207–2211.
     [Google Scholar]
  18. Hill, D., Combee, C. & Bacon, J. (2006) Over/under acquisition and data processing: The next quantum leap in seismic technology?First Break, 24, 81–96.
     [Google Scholar]
  19. Hubral, P., Schleichert, J. & Tygel, M. (1996) A unified approach to 3‐D seismic reflection imaging, Part I: Basic concepts. Geophysics, 61, 742–758.
     [Google Scholar]
  20. de Jonge, T., Vinje, V., Poole, G., Hou, S. & Iversen, E. (2021) De‐bubbling Seismic Data using a Generalized Neural Network. Geophysics, 87, V1–V14.
     [Google Scholar]
  21. Jovanovich, D.B., Sumner, R.D. & Akins‐Easterlin, S.L. (1983) Ghosting and marine signature deconvolution: A prerequisite for detailed seismic interpretation. Geophysics, 48, 1468–1485.
     [Google Scholar]
  22. King, S. & Poole, G. (2015) Hydrophone‐only receiver deghosting using a variable sea surface datum. In: SEG Technical Program Expanded Abstracts. SEG, pp. 4610–4614.
     [Google Scholar]
  23. Klochikhina, E., Crawley, S., Frolov, S., Chemingui, N. & Martin, T. (2020) Leveraging deep learning for seismic image denoising. First Break, 38, 41–48.
     [Google Scholar]
  24. Li, J., Wang, B., Han, D. & Wang, Y. (2020) Intelligent seismic deblending based deep learning based U‐net. In: 82nd EAGE Annual Conference and Exhibition, 2020. EAGE, pp. 1–5.
     [Google Scholar]
  25. Lucas, A., Iliadis, M., Molina, R. & Katsaggelos, A.K. (2018) Using deep neural networks for inverse problems in imaging: beyond analytical methods. IEEE Signal Processing Magazine, 35, 20–36.
     [Google Scholar]
  26. Martin, G.S., Wiley, R. & Marfurt, K.J. (2006) Marmousi2: An elastic upgrade for Marmousi. Leading Edge (Tulsa, OK), 25, 156–166.
     [Google Scholar]
  27. Martin, T., Brittan, J., Bekara, M. & Koch, K. (2011) 3D shallow water demultiple ‐ Extending the concept. In: 73rd European Association of Geoscientists and Engineers Conference and Exhibition 2011: Unconventional Resources and the Role of Technology. Incorporating SPE EUROPEC 2011, 3. European Association of Geoscientists and Engineers, pp. 2040–2045.
     [Google Scholar]
  28. Mellier, G. & Tellier, N. (2018) Considerations about multi‐sensor solid streamer design. In: EAGE Marine Acquisition Workshop, Oslo, Norway. EAGE, cp‐560‐0000.7.
     [Google Scholar]
  29. Orji, O.C., Söllner, W. & Gelius, L.J. (2012) Effects of time‐varying sea surface in marine seismic data. Geophysics, 77, P33–P43.
     [Google Scholar]
  30. Orji, O.C., Sollner, W. & Gelius, L.J. (2013) Sea surface reflection coefficient estimation. In: Society of Exploration Geophysicists International Exposition and 83rd Annual Meeting, SEG 2013. Expanding Geophysical Frontiers. SEG, pp. 51–55.
     [Google Scholar]
  31. Peng, C., Jin, H. & Wang, P. (2014) Noise attenuation for multi‐sensor streamer data via cooperative de‐noising. In: Society of Exploration Geophysicists International Exposition and 84th Annual Meeting SEG 2014. SEG, pp. 1878–1882.
     [Google Scholar]
  32. Peng, H., Messud, J., Salaun, N., Hammoud, I., Jeunesse, P., Lesieur, T. & Lacombe, C. (2021) Proposal of the Dunet neural network architecture: deghosting example and theoretical analysis. In: 82nd EAGE Annual Conference & Exhibition. EAGE, pp. 1–5.
     [Google Scholar]
  33. Poole, G. (2013) Pre‐migration receiver de‐ghosting and re‐datuming for variable depth streamer data In: Society of Exploration Geophysicists International Exposition and 83rd Annual Meeting, SEG 2013. Expanding Geophysical Frontiers. SEG, pp. 4216–4220.
     [Google Scholar]
  34. Poole, G. & Cooper, J. (2018) Multi‐sensor receiver deghosting using data domain sparseness weights. In: 80th EAGE Conference and Exhibition 2018: Opportunities Presented by the Energy Transition. EAGE, pp. 1–5.
     [Google Scholar]
  35. Poole, G., Cooper, J., King, S. & Wang, P. (2015) 3D source designature using source–receiver symmetry in the shot tau‐px‐py domain. In: 77th EAGE Conference and Exhibition 2015: Earth Science for Energy and Environment. EAGE, pp. 3867–3871.
     [Google Scholar]
  36. Qu, S., Verschuur, E., Zhang, D. & Chen, Y. (2021) Training deep networks with only synthetic data: deep‐learning‐based near‐offset reconstruction for (closed‐loop) surface‐related multiple estimations on shallow‐water field data. Geophysics, 86, A39–A43.
     [Google Scholar]
  37. Rickett, J.E., van Manen, D.J., Loganathan, P. & Seymour, N. (2014) Slanted‐streamer data‐adaptive deghosting with local plane waves. In: 76th EAGE Conference and Exhibition 2014. EAGE, pp. 1–5.
     [Google Scholar]
  38. Ronneberger, O., Fischer, P. & Brox, T. (2015) U‐net: convolutional networks for biomedical image segmentation. In: International Conference on Medical Image Computing and Computer‐Assisted Intervention. Springer, pp. 234–241.
     [Google Scholar]
  39. Santos, L. T., Schleicher, J., Tygel, M. & Hubral, P. (2000a) Seismic modeling by demigration. Geophysics, 65, 1281–1289.
     [Google Scholar]
  40. Santos, L. T., Schleicher, J., Tygel, M. & Hubral, P. (2000b) Modeling, migration, and demigration. Leading Edge (Tulsa, OK), 19, 712–715.
     [Google Scholar]
  41. Schuster, G.T. (1993) Least‐squares cross‐well migration. In: SEG Technical Program Expanded Abstracts. SEG, pp. 110–113.
     [Google Scholar]
  42. Siahkoohi, A., Kumar, R. & Herrmann, F. (2018) Seismic data reconstruction with generative adversarial networks. In: 80th EAGE Conference and Exhibition 2018: Opportunities Presented by the Energy Transition, 2018. EAGE, pp. 1–5.
     [Google Scholar]
  43. Siliqi, R., Payen, T., Sablon, R. & Desrues, K. (2013) Synchronized multi‐level source, a robust broadband marine solution. In: SEG Technical Program Expanded Abstracts 2013. Society of Exploration Geophysicists, pp. 56–60.
     [Google Scholar]
  44. Song, J.G., Gong, Y.L. & Li, S. (2015) High‐resolution frequency‐domain Radon transform and variable‐depth streamer data deghosting. Applied Geophysics, 12, 564–572.
     [Google Scholar]
  45. Soubaras, R. (2010) Deghosting by joint deconvolution of a migration and a mirror migration. In: Annual Meeting SEG Denver 2010 Annual Meeting. SEG, pp. 3406–3410.
     [Google Scholar]
  46. Soubaras, R. & Dowle, R. (2010) Variable‐depth streamer ‐ a broadband marine solution. First Break, 28, 89–96.
     [Google Scholar]
  47. Soubaras, R., Dowle, R. & Sablon, R. (2012) BroadSeis: Enhancing interpretation and inversion with broadband marine seismic.: CSEG Recorder, 37, 41–46.
     [Google Scholar]
  48. Sun, J., Slang, S., Elboth, T., Greiner, T. L., McDonald, S. & [J] Gelius, L. (2019) Attenuation of marine seismic interference noise employing a customized U‐Net. Geophysical Prospecting, 68, 845–871.
     [Google Scholar]
  49. Vrolijk, J.‐W. & Blacquière, G. (2021) Source deghosting of coarsely sampled common‐receiver data using a convolutional neural network. Geophysics, 86, V185–V196.
     [Google Scholar]
  50. Vrolijk, J. & Blacquière, G. (2018) Adaptive deghosting including the rough and time variant sea surface. In: 80th EAGE Conference and Exhibition 2018: Opportunities Presented by the Energy Transition. EAGE, pp. 1–5.
     [Google Scholar]
  51. Vrolijk, J.W. & Blacquiere, G. (2020) Source deghosting of coarsely sampled common‐receiver data using machine learning. In: SEG Technical Program Expanded Abstracts. SEG, pp. 3294–3298.
     [Google Scholar]
  52. Zhang, Z., Masoomzadeh, H. & Wang, B. (2018) Evolution of deghosting process for single‐sensor streamer data from 2D to 3D. Geophysical Prospecting, 66, 975–986.
     [Google Scholar]
  53. Zu, S., Cao, J., Qu, S. & Chen, Y. (2020) Iterative deblending for simultaneous source data using the deep neural network. Geophysics, 85, V131–V141.
     [Google Scholar]
/content/journals/10.1111/1365-2478.13253
Loading
Source and receiver deghosting by demigration‐based supervised learning
Geophysical Prospecting 72, 2443 (2024); https://doi.org/10.1111/1365-2478.13253
/content/journals/10.1111/1365-2478.13253
/content/journals/10.1111/1365-2478.13253
Loading

Data & Media loading...

  • Article Type: Research Article
Keyword(s): data processing; modelling; noise; seismics; signal processing

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