1887
Volume 20 Number 5
  • ISSN: 1569-4445
  • E-ISSN: 1873-0604
PDF

Abstract

ABSTRACT

Diffraction imaging can help better understand small‐scale geological structures. Due to their often‐weak signal, in order to image them, it is necessary to separate diffraction signals from the rest of the wavefield. Many different methods have been developed for diffraction wavefield separation, and the newest trend includes the application of artificial neural networks and deep learning. Available case studies with a deep‐learning approach for diffraction separation show good results when applied to synthetic and sedimentary setting datasets where diffraction signals are either strong or have pronounced characteristics. Examples, however, are missing from crystalline or hardrock geological settings where the signal‐to‐noise ratio is by far lower and diffraction signals are usually within a complex reflectivity medium, have steep tails and are usually incomplete. In this study, we showcase the application of a deep semantic segmentation model on synthetic seismic, real ground‐penetrating radar, and hardrock seismic datasets. Synthetic seismic sections were generated using different random noise levels and coherent noise resembling a complex reflectivity pattern interfering with diffraction tails. For the real GPR dataset, diffraction signals were successfully delineated, although in some locations reflections were picked up because of their similar pixel values as the apex of the diffractions. As for the real seismic dataset, through a number of approaches, we were able to completely delineate a single diffraction within several inlines that was generated from a massive sulphide body. The algorithm also enabled us to recognize an incomplete diffraction, at the edge of the seismic cube, which was never labelled. This diffraction originated from outside of the seismic volume and may be a target for future mineral exploration programmes, thanks to the deep semantic segmentation algorithm providing this possibility.

Loading

Article metrics loading...

/content/journals/10.1002/nsg.12227
2022-09-29
2022-12-09
Loading full text...

Full text loading...

/deliver/fulltext/nsg/20/5/nsg12227.html?itemId=/content/journals/10.1002/nsg.12227&mimeType=html&fmt=ahah

References

  1. Bauer, A., Walda, J. & Gajewski, D. (2021) Wavefield decomposition for diffraction separation with convolutional neural networks. SEG/AAPG/SEPM First International Meeting for Applied Geoscience & Energy, 3584040.
    [Google Scholar]
  2. Bellefleur, G., Cheraghi, S. & Malehmir, A. (2019) Reprocessing legacy 3D seismic data from the Halfmile Lake and Brunswick No. 6 VMS deposits, New Brunswick, Canada. Canadian Journal of Earth Sciences, 56, 569–583.
    [Google Scholar]
  3. Bellefleur, G., Müller, C., Snyder, D. & Matthews, L. (2004) Downhole seismic imaging of a massive sulfide orebody with mode‐converted waves, Halfmile Lake, New Brunswick, Canada. Geophysics, 69, 318–329.
    [Google Scholar]
  4. Berkovitch, A., Belfer, I., Hassin, Y. & Landa, E. (2009) Diffraction imaging by multifocusing. Geophysics, 74, (6), WCA75–WCA81.
    [Google Scholar]
  5. Cheraghi, S., Malehmir, A., Bellefleur, G., Bongajum, E. & Bastani, M. (2013) Scaling behavior and the effects of heterogeneity on shallow 14 seismic imaging of mineral deposits: a case study from Brunswick No. 6 mining area. Canada. Journal of Applied Geophysics, 90, 1–18.
    [Google Scholar]
  6. Coellho, T., Araujo, L., Coimbra1, T., Tygel1, M., Avila, S. & Borin, E. (2019) Automatic detection of diffraction‐apex using fully convolutional networks. 16th International Congress of the Brazilian Geophysical Society
  7. Coimbra, T.A., FaccipieriJ.H., SpeglichJ.H., Gelius, L.‐J. & Tygel, M. (2018) Enhancement of diffractions in prestack domain by means of a finite‐offset double‐square‐root traveltime. Geophysics, 84(1), V81–V96.
    [Google Scholar]
  8. Dave, J.L. & Annan, A.P. (1989) Ground‐penetrating radar for high‐resolution mapping of soul and rock stratigraphy. Geophysical Prospecting, 37(5), 531–551.
    [Google Scholar]
  9. Dell, S. & Gajewksi, D. (2011) Common‐reflection‐surface‐based workflow for diffraction imaging. Geophysics, 76(5), S187–S195.
    [Google Scholar]
  10. Dell, S., Pronevich, A., Kashtan, B. & Gajewski, D. (2013) Diffraction traveltime approximation for general anisotropic media. Geophysics, 78(5), WC15–WC23.
    [Google Scholar]
  11. Dell, S., Walda, D., Hoelker, A. & Gajewksi, D. (2020) Categorizing and correlating diffractivity attributes with seismic‐reflection attributes using autoencoder networks. Geophysics, 85(4), 59–70.
    [Google Scholar]
  12. Dou, Q., Wei, L., Magee, D. & Chon, A.(2017) Real‐time hyperbola recognition and fitting in GPR data. IEEE Transactions on Geoscience and Remote Sensing, 55(1), 51–62.
    [Google Scholar]
  13. Fomel, S. (2002) Applications of plane‐wave destruction filters. Geophysics, 67(6), 1946–1960.
    [Google Scholar]
  14. Fomel, S., Landa, E. & Taner, M.T. (2007) Poststack velocity analysis by separation and imaging of seismic diffractions. Geophysics, 72(6), U89–U94.
    [Google Scholar]
  15. Grasmueck, M., Moser, T.M., Pelissier, M.A., Pajchel, J. & Pomar, K. (2015) Diffraction signatures of fracture intersections. Interpretation, 3, SF55–SF68.
    [Google Scholar]
  16. Grasmueck, M.P. (1996) 3‐D ground‐penetrating radar applied to fracture imaging in gneiss. Geophysics, 61, 1050–1064.
    [Google Scholar]
  17. Karimpouli, S., Malehmir, A., Hassani, H., Nabi‐Bidhendi, M. & Khoshdel, H. (2015) Automated diffraction delineation using an apex‐shifted Radon transform. Journal of Geophysics and Engineering, 12, 199–209.
    [Google Scholar]
  18. Khoshnavaz, M.J., Bóna, A., Hossain, M.S., Urosevic, M. & Chambers, K. (2016) Diffractivity: another attribute for the interpretation of seismic data in hard rock environment, a case study. Interpretation, 4(4), 1N–Y5.
    [Google Scholar]
  19. Kim, S., Seol, J.S., Byun, J., Park, J. & Oh, S. (2020) Extraction of diffraction events from seismic data using deep learning‐based approach. SEG Technical Program Expanded Abstracts, 2840–2844.
    [Google Scholar]
  20. Klokov, A. & Fomel, S. (2012) Separation and imaging of seismic diffractions using migrated dip‐angle gathers. Geophysics, 77(6), S131–S143.
    [Google Scholar]
  21. Landa, E. & Keydar, S. (1998) Seismic monitoring of diffraction images for detection of local heterogeneities. Geophysics, 63, 1093–1100.
    [Google Scholar]
  22. Li, C., Zhao, J., Peng, S. & Cui, X. (2021) Prestack diffraction separation in the common virtual source gather. Geophysics, 86(2), S113–S124.
    [Google Scholar]
  23. Lin, P., Peng, S., Zhao, J., Cui, X. & Du, W. (2018) Accurate diffraction imaging for detecting small‐scale geologic discontinuities. Geophysics, 83(5), S447–S457.
    [Google Scholar]
  24. Long, J., Shelhamer, E. & Darrell, T. (2015) Fully convolutional networks for semantic segmentation. CoRR, abs/1411.4038v2, https://arxiv.org/abs/1411.4038.
    [Google Scholar]
  25. Lowney, B., Lokmer, I. & O'Brien, G.S. (2021) Multi‐domain diffraction identification: a supervised deep learning technique for seismic diffraction classification. Computers and Geoscience, 155, https://doi.org/10.1016/j.cageo.2021.104845
    [Google Scholar]
  26. Ma, M., Zhang, R. & Ajo‐Franklin, J. (2020) A workflow of separating and imaging diffraction wave by using deep learning network: an application of GPR data. SEG Technical Program Expanded Abstracts, 1920–1924.
  27. Malehmir, A. & Bellefleur, G. (2009) 3D seismic reflection imaging of volcanic‐hosted massive sulphide deposits: insights from re‐processing Halfmile Lake data, New Brunswick, Canada. Geophysics, 74, B209–B219.
    [Google Scholar]
  28. Malehmir, A., Markovic, M., Marsden, P., Gil, A., Buske, S., Sito, L., et al. (2021) Sparse 3D reflection seismic survey for deep‐targeting iron oxide deposits and their host rocks, Ludvika Mines, Sweden. Solid Earth, 12, 483–502.
    [Google Scholar]
  29. Matthews, L. (2002) Base metal exploration: looking deeper and adding value with seismic data. Canadian Society of Exploration Geophysicists Recorder, 27, 37–43.
    [Google Scholar]
  30. Ronneberger, O., Fischer, P. & Brox, T. (2015) U‐Net: convolutional networks for biomedical image segmentation. Medical Image Computing and Computer‐Assisted Intervention, 9351, 234–241.
    [Google Scholar]
  31. Schwarz, B. (2019) Coherent wavefield subtraction for diffraction separation. Geophysics, 84(3), V157–V168.
    [Google Scholar]
  32. Schwarz, B. & Krawczyk, M.C. (2020) Coherent diffraction imaging for enhanced fault and fracture network characterization. Solid Earth, 11, 1891–1907.
    [Google Scholar]
  33. Sheng, T. & Zhao, J. (2022) Separation and imaging of diffractions using a dilated convolutional neural network. Geophysics, 87(3), S117–S127.
    [Google Scholar]
  34. Theune, U., Rokosh, D., Sacchi, M.D. & Schmitt, D.R. (2006) Mapping fractures with GPR: a case study from Turtle Mountain. Geophysics, 71(5), B139–B150.
    [Google Scholar]
  35. Tschannen, V., Ettrich, N., Delescluse, M. & Keuper, J. (2020) Detection of point scatterers using diffraction imaging and deep learning. Geophysical Prospecting, 68(1), 830–844.
    [Google Scholar]
  36. Yuan, H., Montazeri, M., Looms, M.C. & Nielsen, L. (2019) Diffraction imaging of ground‐penetrating radar data. Geophysics, 84(3), H1–H12.
    [Google Scholar]
  37. Wang, H., Chen, Y. & Liu, X. (2020) Separation and imaging of seismic diffractions using a localized rank‐reduction method with adaptively selected ranks. Geophysics, 85(6), V497–V506.
    [Google Scholar]
http://instance.metastore.ingenta.com/content/journals/10.1002/nsg.12227
Loading
/content/journals/10.1002/nsg.12227
Loading

Data & Media loading...

  • Article Type: Research Article
Keyword(s): Deep learning; Diffraction; GPR; Hardrock; Seismic; Semantic segmentation
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