Skip to main content
SpringerLink
Log in

Elastic-Wave Reverse Time Migration Random Boundary-Noise Suppression Based on CycleGAN

  • Published:
Journal of Ocean University of China Aims and scope Submit manuscript

Abstract

In elastic-wave reverse-time migration (ERTM), the reverse-time reconstruction of source wavefield takes advantage of the computing power of GPU, avoids its disadvantages in disk-access efficiency and reading and writing of temporary files, and realizes the synchronous extrapolation of source and receiver wavefields. Among the existing source wavefield reverse-time reconstruction algorithms, the random boundary algorithm has been widely used in three-dimensional (3D) ERTM because it requires the least storage of temporary files and low-frequency disk access during reverse-time migration. However, the existing random boundary algorithm cannot completely destroy the coherence of the artificial boundary reflected wavefield. This random boundary reflected wavefield with a strong coherence would be enhanced in the cross-correlation image processing of reverse-time migration, resulting in noise and fictitious image in the migration results, which will reduce the signal-to-noise ratio and resolution of the migration section near the boundary. To overcome the above issues, we present an ERTM random boundary-noise suppression method based on generative adversarial networks. First, we use the Resnet network to construct the generator of CycleGAN, and the discriminator is constructed by using the PatchGAN network. Then, we use the gradient descent methods to train the network. We fix some parameters, update the other parameters, and iterate, alternate, and continuously optimize the generator and discriminator to achieve the Nash equilibrium state and obtain the best network structure. Finally, we apply this network to the process of reverse-time migration. The snapshot of noisy wavefield is regarded as a 2D matrix data picture, which is used for training, testing, noise suppression, and imaging. This method can identify the reflected signal in the wavefield, suppress the noise generated by the random boundary, and achieve denoising. Numerical examples show that the proposed method can significantly improve the imaging quality of ERTM.

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

  • Chang, W., and Mcmechan, G. A., 1987. Elastic reverse-time migration. Geophysics, 52(10): 243–256, DOI: https://doi.org/10.1190/1.1442249.

    Article  Google Scholar 

  • Clapp, R. G., 2009. Reverse time migration with random boundaries. 79th Annual International Meeting, SEG Expanded Abstracts. Houston, 1–10, DOI: https://doi.org/10.1190/1.3255432.

  • Clapp, R. G., and Shen, X. K., 2015. Random boundary condition for memory-efficient waveform inversion gradient computation. Geophysics, 80(6): R351–R359.

    Article  Google Scholar 

  • Dablain, M. A., 1986. The application of high-order differencing to the scalar wave equation. Geophysics, 51(1): 54, DOI: https://doi.org/10.1190/1.1442040.

    Article  Google Scholar 

  • Dellinger, J., and Etgen, J., 1990. Wave-field separation in two-dimensional anisotropic media. Geophysics, 55(7): 914, DOI: https://doi.org/10.1190/1.1442906.

    Article  Google Scholar 

  • Dong, J. J., Tang, J., Zhou, R. Z., and Yang, C. Y., 2021. Research on adaptive denoising of one-dimensional time-varying signal based on cyclic generation countermeasure network. Electromechanical Engineering Technology, 50(5): 10–12 (in Chinese with English abstract).

    Google Scholar 

  • Dong, L. G., Ma, Z. T., and Cao, J. Z., 2000. Stability of the staggered-grid high-order difference method for first-order elastic wave equation. Chinese Journal of Geophysics, 43(6): 904–913, DOI: https://doi.org/10.1002/cjg2.107.

    Article  Google Scholar 

  • Duan, Y., and Sava, P., 2015. Scalar imaging condition for elastic reverse time migration. Geophysics, 80(4): S127–S136, DOI: https://doi.org/10.1190/geo2014-0453.1.

    Article  Google Scholar 

  • Dussaud, E., Symes, W. W., Williamson, P., Lemaistre, L., and Cherrett, A., 2008. Computational strategies for reverse-time migration. SEG Technical Program Expanded Abstracts. Vegas, 2267–2271.

  • Feng, B., and Wang, H. Z., 2012. Reverse time migration with source wavefield reconstruction strategy. Journal of Geophysics and Engineering, 9(1): 69–74.

    Article  Google Scholar 

  • Goodfellow, I. J., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., et al., 2014. Generative adversarial networks. Advances in Neural Information Processing Systems, 27: 2672–2680, DOI: https://doi.org/10.1145/3422622.

    Google Scholar 

  • Kaneko, T., and Kameoka, H., 2018. CycleGAN-VC: Non-parallel voice conversion using cycle-consistent adversarial networks. 2018 26th European Signal Processing Conference (EU-SIPCO). Rome, 2100–2140, DOI: https://doi.org/10.23919/EUSIPCO.2018.8553236.

  • Mauricio, A., Joseph, J., Amir, A., and Taylor, D., 2018. Deep-learning tomography. The Leading Edge, 37(1): 58–66, DOI: https://doi.org/10.1190/tle37010058.1.

    Article  Google Scholar 

  • McMechan, G. A., 1983. Migration by extrapolation of time-dependent boundary values. Geophysical Prospecting, 31(3): 413–420.

    Article  Google Scholar 

  • Ratliff, L. J., Burden, S. A., and Sastry, S. S., 2006. Characterization and computation of local Nash equilibria in continuous games. 2013 51st Annual Allerton Conference on Communication, Control, and Computing (Allerton). Monticello, 917–924, DOI: https://doi.org/10.1109/Allerton.2013.6736623.

  • Shrivastava, A., Pfister, T., Tuzel, O., Susskind, J., Wang, W. D., and Webb, R., 2017. Learning from simulated and unsupervised images through adversarial training. 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Honolulu, 2242–2251, DOI: https://doi.org/10.1109/CVPR.2017.241.

  • Song, J., 2020. Binary generative adversarial networks for image retrieval. International Journal of Computer Vision, 128: 2243–2264.

    Article  Google Scholar 

  • Symes, W. W., 2007. Reverse time migration with optimal checkpointing. Geophysics, 72(5): 213–221.

    Article  Google Scholar 

  • Tang, C., and Mcmechan, G. A., 2018. Elastic reverse time migration with a combination of scalar and vector imaging conditions. SEG Technical Program Expanded Abstracts 2018. Anaheim, 4453–4457, DOI: https://doi.org/10.1190/segam2018-2998139.1.

  • Virieux, J., 1984. SH-wave propagation in heterogeneous media: Velocity-stress finite-difference method. Exploration Geophysics, 51(4): 265, DOI: https://doi.org/10.1071/EG984265a.

    Article  Google Scholar 

  • Wang, W. L., and McMechan, G. A., 2015. Vector-based elastic reverse time migration. Geophysics, 80(6): S245–S258, DOI: https://doi.org/10.1190/geo2014-0620.1.

    Article  Google Scholar 

  • Wang, W. L., McMechan, G. A., and Zhang, Q. S., 2015. Comparison of two algorithms for isotropic elastic P and S vector decomposition. Geophysics, 80(4): T147–T160, DOI: https://doi.org/10.1190/geo2014-0563.1.

    Article  Google Scholar 

  • Yan, J., and Sava, P., 2008. Isotropic angle-domain elastic reverse-time migration. Geophysics, 73(6): S229–S239, DOI: https://doi.org/10.1190/1.2981241.

    Article  Google Scholar 

  • Yang, P., Gao, J., and Wang, B., 2014. RTM using effective boundary saving: A staggered grid GPU implementation. Computers & Geosciences, 68: 64–72.

    Article  Google Scholar 

  • Yoon, K., and Marfurt, K. J., 2006. Reverse-time migration using the poynting vector. Exploration Geophysics, 37(1): 102–106.

    Article  Google Scholar 

  • Yue, P., Dechang, P., Junfu, C., and Han, M., 2021. FDPPGAN: Remote sensing image fusion based on deep perceptual patch-GAN. Neural Computing and Applications, 33(15): 1–17, DOI: https://doi.org/10.1007/S00521-021-05724-1.

    Google Scholar 

  • Zeng, Y. Q., He, J. Q., and Liu, Q. H., 2001. The application of the perfectly matched layer in numerical modeling of wave propagation in poroelastic media. Geophysics, 66(4): 1258–1266, DOI: https://doi.org/10.1190/1.1487073.

    Article  Google Scholar 

  • Zhang, L. M., and Cheng, G., 2017. Random boundary conditions for parameter combination optimization and its application in seismic RTM. Geophysical and Geochemical Exploration, 41(5): 890–898 (in Chinese with English abstract).

    Google Scholar 

  • Zhu, H. J., 2017. Elastic wavefield separation based on the Helmholtz decomposition. Geophysics, 82(2): S173–S183, DOI: https://doi.org/10.1190/geo2016-0419.1.

    Article  Google Scholar 

  • Zhu, J. Y., Park, T., Isola, P., and Efros, A. A., 2017. Unpaired image-to-image translation using cycle-consistent adversarial networks. 2017 IEEE International Conference on Computer Vision (ICCV). Venice, 2242–2251, DOI: https://doi.org/10.1109/ICCV.2017.244.

Download references

Acknowledgements

The study is supported by the National Natural Science Foundation of China (No. 41674118) and the Fundamental Research Funds for the Central Universities of China (No. 201964017).

Author information

Authors and Affiliations

  1. Key Laboratory of the Ministry of Education for Seafloor Science and Detection Technology, Ocean University of China, Qingdao, 266100, China

    Guohao Xu & Bingshou He

  2. Functional Laboratory of Marine Mineral Resources Evaluation and Exploration Technology, Qingdao National Laboratory of Marine Science and Technology, Qingdao, 266100, China

    Guohao Xu & Bingshou He

Authors
  1. Guohao Xu
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Bingshou He
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Bingshou He.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Xu, G., He, B. Elastic-Wave Reverse Time Migration Random Boundary-Noise Suppression Based on CycleGAN. J. Ocean Univ. China 21, 849–860 (2022). https://doi.org/10.1007/s11802-022-5171-3

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11802-022-5171-3

Key words

Search

Navigation