1887
  1. Home
  2. A-Z Publications
  3. Geophysical Prospecting
  4. Volume 72, Issue 1
  5. Article
Volume 72 Number 1
  • E-ISSN: 1365-2478

Abstract

ABSTRACT

Deep learning has shown excellent performance in simulating complex nonlinear mappings from the seismic data to elastic parameters. However, seismic acoustic impedance estimated from a direct mapping from seismic waveform data to P‐wave impedance (single‐input network) is hampered by the limited frequency bands. In this paper, we propose to incorporate the low‐frequency impedance model to constrain the inversion (multi‐input network). We add a feature fusion layer to force the lateral smoothness. Besides, usually, a given seismic survey is likely to contain only a few well logs, which is insufficient for conventional deep‐learning ‐based methods to learn the complex mapping from seismic data to elastic parameters. The problem is compounded by the fact that a network trained with synthetic data (compensated for the lack of logs) cannot be directly used for field data. Therefore, we propose to use transfer learning to mitigate this issue. The multi‐input neural network is trained using synthetics and real data in two stages. We carry out experiments to demonstrate that the two‐step training multi‐input network approach has high accuracy in the time direction, excellent continuity in the lateral direction and favourable robustness. Synthetic and field data examples demonstrate that the proposed network can accurately predict impedance even with limited logging data, which provides a reference for oil and gas exploration in the actual production process.

© 2024 European Association of Geoscientists & Engineers. © 2022 European Association of Geoscientists & Engineers.
Loading

Article metrics loading...

/content/journals/10.1111/1365-2478.13229
2023-12-18
2025-05-24

  • From This Site

    /content/journals/10.1111/1365-2478.13229
    dcterms_title,dcterms_subject,pub_keyword
    -contentType:Journal -contentType:Contributor -contentType:Concept -contentType:Institution
    10
    5
Loading full text...

Full text loading...

References

  1. Alfarraj, M. and AlRegib, G. (2019) Semi‐supervised learning for acoustic impedance inversion. In: 89th Annual International Meeting, SEG, Expanded Abstracts. SEG, pp. 2298–2302.
     [Google Scholar]
  2. bin Waheed, U., Haghighat, E., Alkhalifah, T., Song, C. and Hao, Q. (2021) PINNeik: Eikonal solution using physics‐informed neural networks. Computers & Geosciences, 155, 104833.
     [Google Scholar]
  3. Biswas, R., Sen, M.K., Das, V. and Mukerji, T. (2019) Prestack and poststack inversion using a physics‐guided convolutional neural network. Interpretation, 7, SE161–SE174.
     [Google Scholar]
  4. Bordignon, F.L., de Figueiredo, L.P., Azevedo, L., Soares, A., Roisenberg, M. and Neto, G.S. (2017) Hybrid global stochastic and Bayesian linearized acoustic seismic inversion methodology. IEEE Transactions on Geoscience and Remote Sensing, 55, 4457–4464.
     [Google Scholar]
  5. Carron, D. (1989) High resolution acoustic impedance cross‐sections from wireline and seismic data. In SPWLA 30th Annual Logging Symposium, OnePetro. Society of Professional Well Log Analysts, pp. 1–5.
     [Google Scholar]
  6. Cooke, D.A. and Schneider, W.A. (1983) Generalized linear inversion of reflection seismic data. Geophysics, 48, 665–665–676.
     [Google Scholar]
  7. Das, V., Pollack, A., Wollner, U. and Mukerji, T. (2019) Convolutional neural network for seismic impedance inversion. Geophysics, 84, R869–R880.
     [Google Scholar]
  8. de Figueiredo, L.P., Santos, M., Roisenberg, M., Schwedersky Neto, G. and Figueiredo, W. (2014) Bayesian framework to wavelet estimation and linearized acoustic inversion. IEEE Geoscience and Remote Sensing Letters, 11, 2130–2134.
     [Google Scholar]
  9. Ferguson, R.J. and Margrave, G.F. (1996) A simple algorithm for band‐limited impedance inversion. CREWES Research Report, 8, 1–10.
     [Google Scholar]
  10. Gao, Y., Zhao, P., Li, G. and Li, H. (2021) Seismic noise attenuation by signal reconstruction: An unsupervised machine learning approach. Geophysical Prospecting, 69, 984–1002.
     [Google Scholar]
  11. Gholami, A. and Sacchi, M.D. (2012) A fast and automatic sparse deconvolution in the presence of outliers. IEEE Transactions on Geoscience and Remote Sensing, 50, 4105–4116.
     [Google Scholar]
  12. He, K., Zhang, X., Ren, S. and Sun, J. (2016) Deep residual learning for image recognition. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. IEEE, pp. 770–778.
     [Google Scholar]
  13. Huang, C., Zhu, T. (2020) Towards real‐time monitoring: Data assimilated time‐lapse full waveform inversion for seismic velocity and uncertainty estimation. Geophysical Journal International, 223, 811–824.
     [Google Scholar]
  14. Kingma, D.P. and Ba, J. (2014) Adam: A method for stochastic optimization [Preprint]. arXiv:1412.6980.
     [Google Scholar]
  15. LeCun, Y., Bengio, Y. and Hinton, G. (2015) Deep learning. Nature, 521, 436–444.
     [Google Scholar]
  16. Li, S., Liu, B., Ren, Y., Chen, Y., Yang, S., Wang, Y. and Jiang, P. (2020) Deep learning inversion of seismic data. IEEE Transactions on Geoscience and Remote Sensing, 58, 2135–2149.
     [Google Scholar]
  17. Li, Y., Alkhalifah, T. and Zhang, Z.D. (2021) Deep‐learning assisted regularized elastic full waveform inversion using the velocity distribution information from wells. Geophysical Journal International, 226, 1322–1335.
     [Google Scholar]
  18. Lindseth, R.O. (1979) Synthetic sonic logs—a process for stratigraphic interpretation. Geophysics, 44, 3–26.
     [Google Scholar]
  19. Liu, X., Li, B., Li, J., Chen, X., Li, Q. and Chen, Y. (2021) Semi‐supervised deep autoencoder for seismic facies classification. Geophysical Prospecting, 69, 1295–1315.
     [Google Scholar]
  20. Martin, G.S., Wiley, R. and Marfurt, K.J. (2006) Marmousi2: an elastic upgrade for Marmousi. The Leading Edge, 25, 156–156–166.
     [Google Scholar]
  21. Meng, J., Wang, S., Cheng, W., Wang, Z. and Yang, L. (2022) AVO inversion based on transfer learning and low‐frequency model. IEEE Geoscience and Remote Sensing Letters, 19, 1–5.
     [Google Scholar]
  22. Meng, J., Wang, S., Wang, Z., Zhou, C., Yang, L. and Niu, G. (2021) Acoustic impedance inversion based on transfer learning combined with convolutional neural network and residual network. In: 82nd Conference and Exhibition, EAGE, Extended Abstracts. EAGE, 1–5.
     [Google Scholar]
  23. Mustafa, A., Alfarraj, M. and AlRegib, G. (2021) Joint learning for spatial context‐based seismic inversion of multiple datasets for improved generalizability and robustness. Geophysics, 86, 1–50.
     [Google Scholar]
  24. Oldenburg, D., Scheuer, T. and Levy, S. (1983) Recovery of the acoustic impedance from reflection seismograms. Geophysics, 48, 1318–1337.
     [Google Scholar]
  25. Pan, S.J. and Yang, Q. (2010) A survey on transfer learning. IEEE Transactions on Knowledge and Data Engineering, 22, 1345–1359.
     [Google Scholar]
  26. Park, M.J. and Sacchi, M.D. (2020) Automatic velocity analysis using convolutional neural network and transfer learning. Geophysics, 85, V33–V43.
     [Google Scholar]
  27. Robinson, E.A. (1957) Predictive decomposition of seismic traces. Geophysics, 22, 767–778.
     [Google Scholar]
  28. Robinson, E.A. (1967) Predictive decomposition of time series with application to seismic exploration. Geophysics, 32, 418–484.
     [Google Scholar]
  29. Sacchi, M.D. (1997) Reweighting strategies in seismic deconvolution. Geophysical Journal International, 129, 651–656.
     [Google Scholar]
  30. Sang, W., Yuan, S., Yong, X., Jiao, X. and Wang, S. (2021) DCNNs‐based denoising with a novel data generation for multidimensional geological structures learning. IEEE Geoscience and Remote Sensing Letters, 18, 1861–1865.
     [Google Scholar]
  31. Simonyan, K. and Zisserman, A. (2014) Very deep convolutional networks for large‐scale image recognition [arXiv Preprint]. arXiv:1409–1556.
     [Google Scholar]
  32. Sui, Y. and Ma, J. (2019) A nonstationary sparse spike deconvolution with anelastic attenuation. Geophysics, 84, R221–R234.
     [Google Scholar]
  33. Sun, J., Innanen, K.A. and Huang, C. (2021) Physics‐guided deep learning for seismic inversion with hybrid training and uncertainty analysis. Geophysics, 86, R303–R317.
     [Google Scholar]
  34. Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., et al. (2015) Going deeper with convolutions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. IEEE, pp. 1–9.
  35. Velis, D.R. (2008) Stochastic sparse‐spike deconvolution. Geophysics, 73, R1–R9.
     [Google Scholar]
  36. Vest, R.T. (1990) Seismic data inversion using geologic constraints. In: SEG Technical Program Expanded Abstracts. SEG, pp. 1151–1153.
     [Google Scholar]
  37. Wang, L., Meng, D. and Wu, B. (2021a) Seismic inversion via closed‐loop fully convolutional residual network and transfer learning. Geophysics, 86, 1–54.
     [Google Scholar]
  38. Wang, L., Zhao, Q., Gao, J., Xu, Z., Fehler, M. and Jiang, X. (2016) Seismic sparse‐spike deconvolution via Toeplitz‐sparse matrix factorization. Geophysics, 81, V169–V182.
     [Google Scholar]
  39. Wang, W., McMechan, G.A., Ma, J. and Xie, F. (2021b) Automatic velocity picking from semblances with a new deep‐learning regression strategy: comparison with a classification approach. Geophysics, 86, U1–U13.
     [Google Scholar]
  40. Wang, Y., Wang, B., Tu, N. and Geng, J. (2020a) Seismic trace interpolation for irregularly spatial sampled data using convolutional autoencoder. Geophysics, 85, V119–V130.
     [Google Scholar]
  41. Wang, Y., Ge, Q., Lu, W. and Yan, X. (2020b) Well‐logging constrained seismic inversion based on closed‐loop convolutional neural network. IEEE Transactions on Geoscience and Remote Sensing, 58, 5564–5574.
     [Google Scholar]
  42. Wang, Z., Gao, J., Zhao, H., Zhang, B. and Gao, Z. (2021c) A new approach for blind nonlinear acoustic impedance inversion. In: IEEE Geoscience and Remote Sensing Letters. 19, 1–5. https://doi.org/10.1109/LGRS.2020.3047495.
  43. Wu, B., Meng, D., Wang, L., Liu, N. and Wang, Y. (2020) Seismic impedance inversion using fully convolutional residual network and transfer learning. IEEE Geoscience and Remote Sensing Letters, 17, 2140–2144.
     [Google Scholar]
  44. Wu, H., He, Y., Chen, Y., Li, S. and Peng, Z. (2019a) Seismic acoustic impedance inversion using mixed second‐order fractional ATpV regularization. IEEE Access, 8, 3442–3452.
     [Google Scholar]
  45. Wu, X., Yan, S., Bi, Z., Zhang, S. and Si, H. (2021) Deep learning for multidimensional seismic impedance inversion. Geophysics, 86, R735–R745.
     [Google Scholar]
  46. Wu, X., Liang, L., Shi, Y. and Fomel, S. (2019b) FaultSeg3D: Using synthetic data sets to train an end‐to‐end convolutional neural network for 3D seismic fault segmentation. Geophysics, 84, IM35–IM45.
     [Google Scholar]
  47. Yang, F. and Ma, J. (2019) Deep‐learning inversion: A next‐generation seismic velocity model building method. Geophysics, 84, R583–R599.
     [Google Scholar]
  48. Yang, L., Chen, W., Wang, H. and Chen, Y. (2021a) Deep learning seismic random noise attenuation via improved residual convolutional neural network. IEEE Transactions on Geoscience and Remote Sensing, 59, 7968–7981.
     [Google Scholar]
  49. Yang, L., Wang, S., Chen, X., Saad, O.M., Chen, W., Oboué, Y.A.S.I. and Chen, Y. (2021b) Unsupervised 3‐D random noise attenuation using deep skip autoencoder. IEEE Transactions on Geoscience and Remote Sensing, 60, 1–16.
     [Google Scholar]
  50. Yang, L., Wang, S., Chen, X., Chen, W., Saad, O.M., Zhou, X., et al. (2022) High‐fidelity permeability and porosity prediction using deep learning with the self‐attention mechanism. IEEE Transactions on Neural Networks and Learning Systems. Early Access. https://doi.org/10.1109/TNNLS.2022.3157765.
     [Google Scholar]
  51. Yu, S. and Ma, J. (2021) Deep learning for geophysics: Current and future trends. Reviews of Geophysics, 59, e2021RG000742.
     [Google Scholar]
  52. Yuan, S., Wang, S., Luo, Y., Wei, W. and Wang, G. (2019) Impedance inversion by using the low‐frequency full‐waveform inversion result as an a priori model. Geophysics, 84, R149–R164.
     [Google Scholar]
  53. Yuan, S., Wang, S., Luo, C. and He, Y. (2015) Simultaneous multitrace impedance inversion with transform‐domain sparsity promotion. Geophysics, 80, R71–R80.
     [Google Scholar]
  54. Zhang, J., Li, J., Chen, X., Li, Y., Huang, G. and Chen, Y. (2021) Robust deep learning seismic inversion with a priori initial model constraint. Geophysical Journal International, 225, 2001–2019.
     [Google Scholar]
  55. Zhang, R. and Castagna, J. (2011) Seismic sparse‐layer reflectivity inversion using basis pursuit decomposition. Geophysics, 76, R147–R158.
     [Google Scholar]
  56. Zhang, Z.D., Alkhalifah, T., Naeini, E.Z. and Sun, B. (2018) Multiparameter elastic full waveform inversion with facies‐based constraints. Geophysical Journal International, 213, 2112–2127.
     [Google Scholar]
  57. Zhang, Z.D. and Alkhalifah, T. (2019) Regularized elastic full‐waveform inversion using deep learning. Geophysics, 84, R741–R751.
     [Google Scholar]
  58. Zhang, Z.D. and Alkhalifah, T. (2020) High‐resolution reservoir characterization using deep learning‐aided elastic full‐waveform inversion: the North Sea field data example. Geophysics, 85, WA137–WA146.
     [Google Scholar]
  59. Zhao, L., Zou, C., Chen, Y., Shen, W., Wang, Y., Chen, H. and Geng, J. (2021) Fluids and lithofacies prediction based on integration of well‐log data and seismic inversion: a machine learning approach. Geophysics, 86, 1–67.
     [Google Scholar]
/content/journals/10.1111/1365-2478.13229
Loading
Seismic impedance inversion using a multi‐input neural network with a two‐step training strategy
Geophysical Prospecting 72, 107 (2023); https://doi.org/10.1111/1365-2478.13229
/content/journals/10.1111/1365-2478.13229
/content/journals/10.1111/1365-2478.13229
Loading

Data & Media loading...

  • Article Type: Research Article
Keyword(s): Deep learning; Multi‐input network; Seismic impedance inversion; Transfer 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