1887
Volume 51, Issue 6
  • ISSN: 0812-3985
  • E-ISSN: 1834-7533

Abstract

Seismic data interpolation is a meaningful research topic in the field of seismic data processing. In this paper, we propose deep internal learning for interpolating regularly sampled aliased seismic data, to improve the upsampling accuracy of regularly sampled aliased seismic data. The proposed algorithm, contrary to previous deep external learning-based seismic interpolation relying on prior training for vast external seismic data, exploits the characteristics of the field data itself, based on the feature similarity between the regularly missing and remaining samples. Internal learning generates training samples solely from the currently remaining regularly undersampled seismic data, and then trains a simple convolutional neural network using the training set. Finally, the trained model is used to upsample the current seismic traces regularly with high accuracy, and can adapt itself intelligently to different field data for the upsampling requirement. This enables seismic data antialiasing interpolation on regularly sampled seismic data with a small sample in the case of insufficient data. The performance of the proposed deep internal learning is assessed using synthetic and field data, respectively. Moreover, the comparison of the proposed deep internal learning with a classic prediction-based interpolation method and deep external learning-based seismic interpolation validates the effectiveness of the proposed algorithm.

© 2020 Australian Society of Exploration Geophysicists
Loading

Article metrics loading...

/content/journals/10.1080/08123985.2020.1748496
2020-11-01
2026-01-18

  • From This Site

    /content/journals/10.1080/08123985.2020.1748496
    dcterms_title,dcterms_subject,pub_keyword
    -contentType:Journal -contentType:Contributor -contentType:Concept -contentType:Institution
    10
    5
Loading full text...

Full text loading...

References

  1. Abma, R., and J.Claerbout. 1995. Lateral prediction for noise attenuation by t-x and f-x techniques. Geophysics60, no. 6: 1887–96. doi: 10.1190/1.1443920
     https://doi.org/10.1190/1.1443920 [Google Scholar]
  2. Abma, R., and N.Kabir. 2006. 3D interpolation of irregular data with a POCS algorithm. Geophysics71, no. 6: E91–7. doi: 10.1190/1.2356088
     https://doi.org/10.1190/1.2356088 [Google Scholar]
  3. Dong, C., C.C.Loy, and X.Tang. 2016. Accelerating the super-resolution convolutional neural network. European conference on computer vision, Amsterdam, The Netherlands, 391–407.
  4. Fomel, S.2003. Seismic reflection data interpolation with differential offset and shot continuation. Geophysics68, no. 2: 733–44. doi: 10.1190/1.1567243
     https://doi.org/10.1190/1.1567243 [Google Scholar]
  5. Gan, S., S.Wang, Y.Chen, Y.Zhang, and Z.Jin. 2015. Dealiased seismic data interpolation using seislet transform with low-frequency constraint. IEEE Transactions on Geoscience and Remote Sensing Letters12, no. 10: 2150–4. doi: 10.1109/LGRS.2015.2453119
     https://doi.org/10.1109/LGRS.2015.2453119 [Google Scholar]
  6. Gao, J., A.Stanton, M.Naghizadeh, M.D.Sacchi, and X.Chen. 2013. Convergence improvement and noise attenuation considerations for beyond alias projection onto convex sets reconstruction. Geophysical Prospecting61, no. s1: 138–51. doi: 10.1111/j.1365‑2478.2012.01103.x
     https://doi.org/10.1111/j.1365-2478.2012.01103.x [Google Scholar]
  7. Glasner, D., S.Bagon, and M.Irani. 2009. Super-resolution from a single image. IEEE international conference on computer vision, Kyoto, Japan, 349–56.
  8. Goldsborough, P.2016. A tour of TensorFlow. https://arxiv.org/abs/1610.01178 (accessed September 21, 2019).
  9. Gulunay, N.2003. Seismic trace interpolation in the Fourier transform domain. Geophysics68, no. 1: 355–69. doi: 10.1190/1.1543221
     https://doi.org/10.1190/1.1543221 [Google Scholar]
  10. Huang, W., R.Wu, and R.Wang. 2018. Damped dreamlet representation for exploration seismic data interpolation and denoising. IEEE Transactions on Geoscience and Remote Sensing56, no. 6: 3159–72. doi: 10.1109/TGRS.2018.2793856
     https://doi.org/10.1109/TGRS.2018.2793856 [Google Scholar]
  11. Jia, Y., and J.Ma. 2017. What can machine learning do for seismic data processing? An interpolation application. Geophysics82, no. 3: V163–77. doi: 10.1190/geo2016‑0300.1
     https://doi.org/10.1190/geo2016-0300.1 [Google Scholar]
  12. Jia, Y., S.Yu, and J.Ma. 2018. Intelligent interpolation by Monte Carlo machine learning. Geophysics83, no. 2: V83–97. doi: 10.1190/geo2017‑0294.1
     https://doi.org/10.1190/geo2017-0294.1 [Google Scholar]
  13. Kingma, D.P., and J.L.Ba. 2015. Adam: A method for stochastic optimization. International conference on learning representations, San Diego, CA, USA, 1–15.
  14. Li, C., G.Liu, Z.Hao, S.Zu, F.Mi, and X.Chen. 2018. Multidimensional seismic data reconstruction using frequency-domain adaptive prediction-error filter. IEEE Transactions on Geoscience and Remote Sensing56, no. 4: 2328–36. doi: 10.1109/TGRS.2017.2778196
     https://doi.org/10.1109/TGRS.2017.2778196 [Google Scholar]
  15. Liu, G., and X.Chen. 2018. Seismic data interpolation using frequency-domain complex nonstationary autoregression. Geophysical Prospecting66, no. 3: 478–97. doi: 10.1111/1365‑2478.12499
     https://doi.org/10.1111/1365-2478.12499 [Google Scholar]
  16. Liu, W., S.Cao, S.Gan, Y.Chen, S.Zu, and Z.Jin. 2016. One-step slope estimation for dealiased seismic data reconstruction via iterative seislet thresholding. IEEE Geoscience and Remote Sensing Letters13, no. 10: 1462–6. doi: 10.1109/LGRS.2016.2591939
     https://doi.org/10.1109/LGRS.2016.2591939 [Google Scholar]
  17. Liu, Y., and S.Fomel. 2011. Seismic data interpolation beyond aliasing using regularized nonstationary autoregression. Geophysics76, no. 5: V69–77. doi: 10.1190/geo2010‑0231.1
     https://doi.org/10.1190/geo2010-0231.1 [Google Scholar]
  18. Ma, J.2013. Three-dimensional irregular seismic data reconstruction via low-rank matrix completion. Geophysics78, no. 5: V181–92. doi: 10.1190/geo2012‑0465.1
     https://doi.org/10.1190/geo2012-0465.1 [Google Scholar]
  19. Mandelli, S., V.Lipari, P.Bestagini, and S.Tubaro. 2019. Interpolation and denoising of seismic data using convolutional neural networks. https://arxiv.org/abs/1901.07927 (accessed September 21, 2019).
  20. Naghizadeh, M., and M.D.Sacchi. 2007. Multistep autoregressive reconstruction of seismic records. Geophysics72, no. 6: V111–8. doi: 10.1190/1.2771685
     https://doi.org/10.1190/1.2771685 [Google Scholar]
  21. Naghizadeh, M., and M.D.Sacchi. 2009. f-x adaptive seismic-trace interpolation. Geophysics74, no. 1: V9–16. doi: 10.1190/1.3008547
     https://doi.org/10.1190/1.3008547 [Google Scholar]
  22. Naghizadeh, M., and M.D.Sacchi. 2010. Beyond alias hierarchical scale curvelet interpolation of regularly and irregularly sampled seismic data. Geophysics75, no. 6: WB189–202. doi: 10.1190/1.3509468
     https://doi.org/10.1190/1.3509468 [Google Scholar]
  23. Naghizadeh, M., and M.D.Sacchi. 2012. Multidimensional de-aliased Cadzow reconstruction of seismic records. Geophysics78, no. 1: A1–5. doi: 10.1190/geo2012‑0200.1
     https://doi.org/10.1190/geo2012-0200.1 [Google Scholar]
  24. Oliveira, D.A.B., R.S.Ferreira, R.Silva, and E.V.Brazil. 2018. Interpolating seismic data with conditional generative adversarial networks. IEEE Geoscience and Remote Sensing Letters15, no. 12: 1952–6. doi: 10.1109/LGRS.2018.2866199
     https://doi.org/10.1109/LGRS.2018.2866199 [Google Scholar]
  25. Oropeza, V., and M.D.Sacchi. 2011. Simultaneous seismic data denoising and reconstruction via multichannel singular spectrum analysis. Geophysics76, no. 3: V25–32. doi: 10.1190/1.3552706
     https://doi.org/10.1190/1.3552706 [Google Scholar]
  26. Porsani, M.1999. Seismic trace interpolation using half-step prediction filters. Geophysics64, no. 5: 1461–7. doi: 10.1190/1.1444650
     https://doi.org/10.1190/1.1444650 [Google Scholar]
  27. Ronen, J.1987. Wave-equation trace interpolation. Geophysics52, no. 7: 973–84. doi: 10.1190/1.1442366
     https://doi.org/10.1190/1.1442366 [Google Scholar]
  28. Spitz, S.1991. Seismic trace interpolation in the F-X domain. Geophysics56, no. 6: 785–94. doi: 10.1190/1.1443096
     https://doi.org/10.1190/1.1443096 [Google Scholar]
  29. Shocher, A., N.Cohen, and M.Irani. 2018. “Zero-shot” super-resolution using deep internal learning. IEEE conference on computer vision and pattern recognition, Salt Lake City, Utah, USA, 3118–26.
  30. Shahdoosti, H.R., and Z.Rahemi. 2019. Edge-preserving image denoising using a deep convolutional neural network. Signal Processing159: 20–32. doi: 10.1016/j.sigpro.2019.01.017
     https://doi.org/10.1016/j.sigpro.2019.01.017 [Google Scholar]
  31. Wang, B., N.Zhang, W.Lu, and J.Wang. 2019. Deep-learning-based seismic data interpolation: A preliminary result. Geophysics84, no. 1: V11–20. doi: 10.1190/geo2017‑0495.1
     https://doi.org/10.1190/geo2017-0495.1 [Google Scholar]
  32. Zhang, X., Q.Liu, X.Li, Y.Zhou, and C.Zhang. 2016. Non-local feature back-projection for image super-resolution. IET Image Processing10, no. 5: 398–408. doi: 10.1049/iet‑ipr.2015.0467
     https://doi.org/10.1049/iet-ipr.2015.0467 [Google Scholar]
  33. Zu, S., H.Zhou, Y.Chen, X.Pan, S.Gan, and D.Zhang. 2016. Interpolating big gaps using inversion with slope constraint. IEEE Geoscience and Remote Sensing Letters13, no. 9: 1369–73. doi: 10.1109/LGRS.2016.2587301
     https://doi.org/10.1109/LGRS.2016.2587301 [Google Scholar]
/content/journals/10.1080/08123985.2020.1748496
Loading
Seismic data interpolation using deep internal learning
Exploration Geophysics 51, 683 (2020); https://doi.org/10.1080/08123985.2020.1748496
/content/journals/10.1080/08123985.2020.1748496
/content/journals/10.1080/08123985.2020.1748496
Loading

Data & Media loading...

  • Article Type: Research Article
Keyword(s): algorithm; Interpolation; neural network; poststack; prestack

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