AccScience Publishing / JSE / Article
Submit to JSE
Cite this article
6
Views
Journal Browser
Volume | Year
Issue
Search
Forthcoming Issue
Current Issue
View All
News and Announcements
View All
ARTICLE

Transfer learning seismic impedance inversion method based on temporal convolutional networks

ZEFENG WANG1 ,  HONG CAO2 ,  ZHIFANG YANG2 ,  HUIQUN XU1 ,  MENGQIONG YANG1 ,  YASONG ZHAO1
Show Less
1 School of Geophysics and Petroleum Resources, Yangtze University, Wuhan 430100, Hubei Province, P. R. China,
2 Research Institute of Petroleum Exploration and Development, Petrochina, Beijing 100083, P. R. China,
JSE 2022, 31(4), 391–405;
Submitted: 9 June 2025 | Revised: 9 June 2025 | Accepted: 9 June 2025 | Published: 9 June 2025
© 2025 by the Authors. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution -Noncommercial 4.0 International License (CC-by the license) ( https://creativecommons.org/licenses/by-nc/4.0/ )
Download PDF
Cite
XML
Abstract

Wang, Z.F., Cao, H., Yang, Z.F., Xu, H.Q., Yang, M.Q. and Zhao, Y., 2022. Transfer learning seismic impedance inversion method based on temporal convolutional networks. Journal of Seismic Exploration, 31: 391-405. The nonlinear mapping between seismic data and impedance can be established by Temporal Convolutional Networks (TCN), which has been proved by forward modeling data. However, whether the deep neural network can be used to train an inversion mapping model with good generalization ability under a small number of labeled samples remains to be explored. In view of this, the noise analysis of the TCN seismic impedance inversion method was firstly carried out, and the model test showed that the TCN seismic impedance inversion method had certain noise resistance. Secondly, an inversion mapping model was obtained based on the training of Marmousi-2 data set, and then five traces of Overthrust model samples were added for fine-tuning to obtain a new inversion mapping model. The inversion of Overthrust was performed based on the TCN transfer learning inversion mapping model. And the model test results showed that: with a small number of labels, the inversion results of the Overthrust dataset based on TCN transfer learning are higher than the Pearson sum determination results obtained by TCN inversion, and the error profile is relatively small compared to the true impedance. Furthermore, TCN transfer learning method ,which was effectively proved in adjacent blocks of the actual data, compared with the result of the TCN inversion. Therefore, the introduction of transfer learning in TCN seismic impedance inversion can improve the generalization ability of the inversion mapping model trained with a few labeled samples in practical application.

Keywords
temporal convolutional network
transfer learning
fine-tuning
seismic impedance inversion
References
  1. Alfarraj, M. and Alregib, G., 2019. Semi-supervised learning for acoustic impedance
  2. inversion. Expanded Abstr., 89th Ann. Internat. SEG Mtg., San Antonio.
  3. doi: 10.1190/segam2019-3215902.1.
  4. Bai, S.J., Kolter, J.Z. and Koltun, V., 2018. An empirical evaluation of generic
  5. convolutional and recurrent networks for sequence modeling. arxiv:1803.01271.
  6. Cao, L.L., Li, H.T., Han, Y.S., Yu, F., Gu, H.Y., 2016. Application of convolutional neural
  7. networks in classification of high resolution remote sensing imagery. Sci.
  8. Survey.mapp., 41(9): 170-175. doi:10.16251/j.cnki.1009-2307.2016.09.033.
  9. Das, V., Pollack, A., Wollner, U. and Mukerji, T., 2019. Convolutional neural network for
  10. seismic impedance inversion. Geophysics, 84(6): R869-R880.
  11. Guo, R., Zhang, J.J., Liu, D., Zhang, Y.B. and Zhang, D.W., 2019. Application of bi-
  12. directional long short-term memory recurrent neural network for seismic impedance
  13. inversion. Extended Abstr., 81st EAGE Conf., London: 3-6.
  14. doi: 10.3997/2214-4609.201901386.
  15. He, Q. and Wang, Y., 2020. Reparameterized full waveform inversion using deep neural
  16. networks. Geophysics, 86(1): 1-71.
  17. Hochreiter, S. and Schmidhuber, J., 1997. Long short-term memory. Neural Computat.,
  18. 9(8). doi:10.1162/neco.1997.9.8.1735.
  19. Hou, Y.M., Zhou, H.M. and Wang, Z.Y., 2017. Overview of speech recognition based on
  20. deep learning. Applict. Res. Comput., 34: 2241-2246.
  21. doi: 10.3969/j.issn.1001-3695.2017.08.001.
  22. Huang, X.R., Dai, Y., Xu, Y.G. and Tang, Y., 2020. Seismic inversion experiments based
  23. on different datasets of deep learning algorithm. J. SW Petrol. Univ. (Nat. Sci. Ed.),
  24. 42(6): 16-25.
  25. Lecun, Y. and Bottou, L., 1998. Gradient-based learning applied to document recognition.
  26. Proc. IEEE Conf., 86: 2278-2324.
  27. Li, S., Liu, B., Ren, Y., Chen, Y. and Jiang, P., 2020. Deep-learning inversion of seismic
  28. Data. IEEE Transactions on Geoscience and Remote Sensing, 57: 2135-2149.
  29. Liu, L.N,, Liu, H. and Li, Y.M., 2004.Wave-equation 3-D prestack depth migration for the
  30. SEG/EAGE salt and overthrust model. Chin. J. Geophys, 47(2): 312-320.
  31. Long, J., Shelhamer, E. and Darrell, T., 2015. Fully convolutional networks for semantic
  32. segmentation. IEEE Transact. Patt. Analys. Mach. Intellig. 39: 640-651.
  33. Lu, H.T. and Zhang, Q.C., 2016. Applications of deep convolutional neural network in
  34. computer vision. J. Acquis. Proces., 31: 1-17. doi:10.16337/j.1004-9037.2016.01.001.
  35. Martin, G.S., Wiley, R. and Marfurt, K.J., 2006. Marmousi-2: An elastic upgrade for
  36. Marmousi. The Leading Edge, 25:156-166.
  37. Mustafa, A., Alfarraj, M. and Alregib, G., 2019. Estimation of acoustic impedance from
  38. seismic data using temporal convolutional network. Extended Abstr., 81st EAGE
  39. Conf., London. arxiv:1906.02684.
  40. Pascanu, R., Gulcehre, C., Cho, K. and Bengio, Y., 2013. How to construct deep recurrent
  41. neural networks. Comput. Sci. arxiv:1312.6026v1.
  42. Richardson, A. and Feller, C., 2019. Seismic data denoising and deblending using deep
  43. learning. arxiv:1907.01497v1.
  44. Shao, R.B., Xiao, L.Z., Liao, G.Z., Zhou, J. and Li, G.J., 2022. A reservoir parameters
  45. prediction method for geophysical logs based on transfer learning. Chin. J. Geophys.
  46. (in Chinese), 65(2):796-808. doi:10.6038/cjg2022P0057.
  47. Song, H., Mao, WJ. and Tang, H.H., 2021. Application of deep neural networks for
  48. multiples attenuation. Chin. J. Geophys. (in Chinese), 64: 2795-2808.
  49. Tzeng, E., Hoffman, J., Zhang, N., Saenko, K. and Darrell, T., 2014. Deep domain
  50. confusion: Maximizing for domain invariance. Comput. Sci. arxiv:1412.3474v1.
  51. Tzeng, E., Hoffman, J., Saenko, K. and Darrell, T., 2017. Simultaneous deep transfer
  52. across domains and tasks, 2015. IEEE Internat. Conf. Comput. Vis. (ICCV). IEEE.
  53. arxiv.org/abs/1510.02192.
  54. Wu, B., Meng, D., Wang, L., Liu, N. and Wang, Y., 2020. Seismic impedance inversion
  55. using fully convolutional residual network and transfer learning. IEEE Geosci.
  56. Remote Sens. Lett., 99:1-5.
  57. Wu, B., Meng, D. and Zhao, H., 2021. Semi-supervised learning for seismic impedance in
  58. version using generative adversarial networks. Remote Sens., 13: 909.
  59. doi:10.3390/rs13050909.
  60. Yosinski, J., Clune, J., Bengio, Y. and Lipson, H., 2014. How transferable are features in
  61. deep neural networks? CoRR, arxiv:1411.1792v1.
  62. Zaremba, W., Sutskever, I. and Vinyals, O., 2014. Recurrent Neural Network Regularizati
  63. on. Eprint Arxiv, arxiv:1409.2329.
  64. Zhang, Y.L., Yu, Z.C., Hu, T.Y. and He, C., 2021. Multi-trace joint downhole microseismic
  65. phase detection and arrival picking method. Chin. J. Geophys. (in Chinese), 64: 2073
  66. -2085. doi:10.6038/cjg202 100379.
  67. Zhuang, F.Z., Luo, P., He, Q.and Shi, Z.Z., 2015. Survey on transfer learning research.
  68. Ruan Jian Xue Bao/Journal of Software,26(1):26-39.
Share
Back to top
Journal of Seismic Exploration, Electronic ISSN: 0963-0651 Print ISSN: 0963-0651, Published by AccScience Publishing
We use cookies on our website to ensure you get the best experience.
Read more about our cookies here
Accept