Skip to main content
SpringerLink
Log in

Research on fault recognition method combining 3D Res-UNet and knowledge distillation

  • Seismic inversion/interpretation
  • Published:
Applied Geophysics Aims and scope Submit manuscript

Abstract

Deep learning technologies are increasingly used in the field of geophysics, and a variety of algorithms based on shallow convolutional neural networks are more widely used in fault recognition, but these methods are usually not able to accurately identify complex faults. In this study, using the advantage of deep residual networks to capture strong learning features, we introduce residual blocks to replace all convolutional layers of the three-dimensional (3D) UNet to build a new 3D Res-UNet and select appropriate parameters through experiments to train a large amount of synthesized seismic data. After the training is completed, we introduce the mechanism of knowledge distillation. First, we treat the 3D Res-UNet as a teacher network and then train the 3D Res-UNet as a student network; in this process, the teacher network is in evaluation mode. Finally, we calculate the mixed loss function by combining the teacher model and student network to learn more fault information, improve the performance of the network, and optimize the fault recognition effect. The quantitative evaluation result of the synthetic model test proves that the 3D Res-UNet can considerably improve the accuracy of fault recognition from 0.956 to 0.993 after knowledge distillation, and the effectiveness and feasibility of our method can be verified based on the application of actual seismic data.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

References

  • Ashraf, H., Mousa, W. A., and Al Dossary S., 2016, Sobel filter for edge detection of hexagonally sampled 3D seismic data: Geophysics, 81(6), N41–N51.

    Article  Google Scholar 

  • Ba, L. J., and Caruana, R., 2014, Do deep nets really need to be deep?: Proceedings of the 27th International Conference on Neural Information Processing Systems, 3, 2654–2662.

    Google Scholar 

  • Bucila, C., Caruana, R., and Niculescu-Mizil, A., 2006, Model compression: Proceedings of the 12th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 535–541.

  • Chopra, S., and Marfurt, K. J., 2005, Seismic attributes—a historical perspective: Geophysics, 70(5), 3–28.

    Article  Google Scholar 

  • Chopra, S, and Marfurt, K. J., 2007, Volumetric curvature attributes add value to 3D seismic data interpretation: The Leading Edge, 26(7), 856–867.

    Article  Google Scholar 

  • Chopra, S. and Marfurt, K. J., 2008, Emerging and future trends in seismic attributes: The Leading Edge, 27(3), 298–318.

    Article  Google Scholar 

  • Chopra, S. and Marfurt, K J., 2012, Seismic attribute expression of differential compaction: The Leading Edge, 31(12), 1418–1422.

    Article  Google Scholar 

  • Cunha, A., Pochet, A., Lopes, H., and 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.

    Article  Google Scholar 

  • Das, V., Pollack, A., and Wollner, U., 2018, Convolutional neural network for seismic impedance inversion: 88th Annual International Meeting, SEG, Expanded Abstracts, 2071–2075.

  • Di, H. and Gao, D., 2014, Gray-level transformation and Canny edge detection for 3D seismic discontinuity enhancement: Computers and Geosciences, 72, 192–200

    Article  Google Scholar 

  • Di, H., Shafiq, M., and AlRegib, G., 2018, Patch-level MLP classification for improved fault detection: 88th Annual International Meeting, SEG, Expanded Abstracts, 2211–2215.

  • Di, H., Li, C., Smith S., Li, Z., and Abubakar, A., 2021, Imposing interpretational constraints on a seismic interpretation convolutional neural network: Geophysics, 86(3), IM63–IM71.

    Article  Google Scholar 

  • Duan, Y., Wu, C., Zheng, X., Huang, Y., and Ma, J., 2018, Coherence based on spectral variance analysis: Geophysics, 83(3), O55–O66.

    Article  Google Scholar 

  • Golik, P., Doetsch, P., and Ney, H., 2013, Cross-entropy vs. squared error training: a theoretical and experimental comparison: Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH, 1756–1760.

  • Guo, B., Li, L., and Luo, Y., 2018, A new method for automatic seismic fault detection using convolutional neural network: 88th Annual International Meeting, SEG, Expanded Abstracts, 1951–1955.

  • He, K., Zhang, X., Ren, S., and Sun, J., 2016, Deep residual learning for image recognition: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 770–778.

  • Hinton, G., Vinyals, O., and Dean, J., 2015, Distilling the knowledge in a neural network: Computer Science, 14(7), 38–39.

    Google Scholar 

  • S., and Szegedy, C., 2015, Batch normalization: accelerating deep network training by reducing internal covariate shift: International Conference on Machine Learning, 37, 448–456.

    Google Scholar 

  • Kingma, D., and Ba, J., 2015, Adam: a method for stochastic optimization: International Conference on Learning Representations (ICLR), 1–15.

  • Lu, X., Huang, H., Li S., and Yin, L.,, 2020, Saltbody classification method based on UNet: Chinese Journal of Computational Physics, 37(03), 327–334.

    Google Scholar 

  • Mandelli, S., Borra, F., Lipari, V., and Bestagini, P., 2018, Seismic data interpolation through convolutional autoencoder: 88th Annual International Meeting, SEG, Expanded Abstracts, 4101–4105.

  • Noh, H., Hong, S., and Han, B., 2015, Learning deconvolution network for semantic segmentation: Proceedings of the IEEE International Conference on Computer Vision, 1520–1528.

  • Pedersen, S. I, Randen, T, Sonneland, L, and Steen, O., 2002-Automatic fault extraction using artificial ants: 72nd Annual International Meeting, SEG, Expanded Abstracts, 512–515.

  • Philips, M., and Formel, S., 2017, Plane-wave Sobel attribute for discontinuity enhancement in seismic images: Geophysics, 82(6), WB63–WB69.

    Article  Google Scholar 

  • Pochet, A., Diniz, P.H.B., Lopes, H., and Gattass, M., 2019, Seismic fault detection using convolutional neural networks trained on synthetic poststacked amplitude maps: IEEE Geoscience and Remote Sensing Letters, 16(3), 352–356.

    Article  Google Scholar 

  • Qi, J., Li, F., and Marfut, K. J., 2017, Multiazimuth coherence: Geophysics, 82(6), O83–O89.

    Article  Google Scholar 

  • Ronneberger, O., Fischer, P., and Brox, T., 2015, UNet: convolutional networks for biomedical image segmentation: International Conference on Medical Image Computing and Computer-Assisted Intervention, 234–241.

  • Stephen, A., 2018, Generative Adversarial Networks in Seismic Data Processing: 88th Annual International Meeting, SEG, Expanded Abstracts, 1991–1995.

  • Wang, B., Zhang, N., and Lu, W., 2018, Deep Learning Based Seismic Data Interpolation: A Prelimirary Result: Geophysics, 81(1), 11–20.

    Google Scholar 

  • Wang, S., Yuan, S., Wang, T., Guo, J., and Li, S., 2018, Three-dimensional geosteering coherence attributes for deep-formation discontinuity detection: Geophysics, 83(6), O105–O113.

    Article  Google Scholar 

  • Wu, X., 2017, Directional structure-tensor-based coherence to detect seismic faults and channels: Geophysics, 82(2), A13–A17.

    Article  Google Scholar 

  • Wu, X. and Hale, D., 2016, 3D seismic image processing for faults: Geophysics, 81(2), IM1–IM11.

    Article  Google Scholar 

  • Wu, X., Shi, Y., and Fomel, S., 2018, Convolutional neural networks for fault interpretation in seismic images: 88th Annual International Meeting, SEG, Expanded Abstracts, 1946–1950.

  • Wu, X., Liang, L., Shi, Y., and Formel, S., 2019, FaultSeg3D: Using synthetic data sets to train an end-to-end convolutional neural network for 3D seismic fault segmentation: Geophysics, 84(3), IM35–IM45.

    Article  Google Scholar 

  • Xiong, W., Ji, X., Ma, Y., Wang, Y., AlBinHassan, N. M., Ali, M. N., and Luo, Y., 2018, Seismic fault detection with convolutional neural network: Geophysics, 83(5), O97–O103.

    Article  Google Scholar 

  • Zagoruyko, S., and Komodakis, N., 2016, Paying more attention to attention: improving the performance of convolutional neural networks via attention transfer: International Conference on Learning Representations (ICLR), 1–13.

  • Zhang, R., Song, P., Liu, B., Zhang, X., Tan, J., Zou, Z., Xie, C., and Wang, S., 2020, Low-frequency swell noise suppression based on UNet: Applied Geophysics, 17(3), 419–431.

    Article  Google Scholar 

  • Zhao, T. and Mukhopadhyay, P., 2018, A fault detection workflow using deep learning and image processing: 88th Annual International Meeting, SEG, Expanded Abstracts, 1966–1969.

Download references

Acknowledgments

The authors thank the Research Institute of Exploration and Development of Dagang Oilfield Company for providing the data and support and express their gratitude to the reviewers for their constructive comments.

Author information

Authors and Affiliations

  1. School of Geosciences, China University of Petroleum (East China), Qingdao, 266580, China

    Jing Wang, Jun-Hua Zhang & Zuoqian Wang

  2. Research Institute of Exploration and Development, Dagang Oilfield Company, PetroChina, Tianjin, 300280, China

    Jia-Liang Zhang, Feng-Ming Lu & Rui-Gang Meng

Authors
  1. Jing Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Jun-Hua Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Jia-Liang Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Feng-Ming Lu
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Rui-Gang Meng
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Zuoqian Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Jun-Hua Zhang.

Additional information

Wang Jing received her bachelor’s degree (2008) in exploration technology and engineering and master’s degree (2011) in geological exploration and information technology from China University of Petroleum (East China). She is currently pursuing PhD in geological resources and geological engineering at China University of Petroleum (East China). She is mainly engaged in seismic data interpretation, focusing on the application of artificial intelligence in the field of geophysical exploration.

Fund Project

This work was supported by the National Natural Science Foundation of China (No. 42072169).

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Wang, J., Zhang, JH., Zhang, JL. et al. Research on fault recognition method combining 3D Res-UNet and knowledge distillation. Appl. Geophys. 18, 199–212 (2021). https://doi.org/10.1007/s11770-021-0894-2

Download citation

  • Received:

  • Revised:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11770-021-0894-2

Keywords

Search

Navigation