1887

Abstract

Summary

Training deep learning models on synthetic data is a common practice in geophysics. However, knowledge transfer from synthetic to field applications is often a bottleneck. Here, we describe the workflow for the generation of a realistic synthetic dataset of elastic waveforms, sufficient for low-frequency extrapolation in marine streamer setup. Namely, we first extract the source signature, the noise imprint, and a 1D velocity model from real marine data. Then, we use those to generate pseudorandom initializations of elastic subsurface models and simulate elastic wavefield data. After that, we enrich the simulated data with realistic noise and use it to train a deep neural network. Finally, we demonstrate the results of low-frequency extrapolation on field streamer data, given that the model was trained exclusively on a synthetic dataset.

Loading

Article metrics loading...

/content/papers/10.3997/2214-4609.202112949
2021-10-18
2024-06-15
Loading full text...

Full text loading...

References

  1. Aharchaou, M., Baumstein, A., Vdovina, T., Lu, R. and Neumann, E.
    [2020] Deep Learning of Bandwidth Extension from Seabed Seismic. In: 82nd EAGE Annual Conference & Exhibition, 2020. European Association of Geoscientists & Engineers, 1–5.
    [Google Scholar]
  2. Fabien-Ouellet, G.
    [2020] Low-frequency generation and denoising with recursive convolutional neural networks. In: SEG Technical Program Expanded Abstracts 2020, Society of Exploration Geophysicists, 870–874.
    [Google Scholar]
  3. Hu, W., Jin, Y., Wu, X. and Chen, J.
    [2020] Physics-guided self-supervised learning for low frequency data prediction in FWI. In: SEG Technical Program Expanded Abstracts 2020, Society of Exploration Geophysicists, 875–879.
    [Google Scholar]
  4. Kalita, M. and Alkhalifah, T.
    [2017] Efficient full waveform inversion using the excitation representation of the source wavefield. Efficient full waveform inversion using the excitation representation of the source wavefield., 210(3), 1581–1594.
    [Google Scholar]
  5. Kazei, V. and Alkhalifah, T.
    [2019] Scattering radiation pattern atlas: What anisotropic elastic properties can body waves resolve?Scattering radiation pattern atlas: What anisotropic elastic properties can body waves resolve?, 124(3), 2781–2811.
    [Google Scholar]
  6. Kazei, V., Ovcharenko, O., Alkhalifah, T. and Simons, F.
    [2019a] Realistically Textured Random Velocity Models for Deep Learning Applications. In: 81st EAGE Conference and Exhibition 2019.
    [Google Scholar]
  7. Kazei, V., Ovcharenko, O., Plotnitskii, P., Peter, D., Zhang, X. and Alkhalifah, T.A.
    [2019b] Mapping seismic data cubes to vertical velocity profiles by deep learning: New full-waveform inversion paradigm?
  8. Kingma, D.P. and Ba, J.
    [2014] Adam: A method for stochastic optimization. arXiv:1412.6980.
  9. Köhn, D.
    [2011] Time domain 2D elastic full waveform tomography. Ph.D. thesis, Christian-Albrechts Universität Kiel.
    [Google Scholar]
  10. Long, A.S., Reiser, C.
    [2014] Ultra-low frequency seismic: Benefits and solutions. In: International Petroleum Technology Conference. International Petroleum Technology Conference.
    [Google Scholar]
  11. Ovcharenko, O., Kazei, V., Kalita, M., Peter, D. and Alkhalifah, T.
    [2019] Deep learning for low-frequency extrapolation from multioffset seismic data. Deep learning for low-frequency extrapolation from multioffset seismic data., 84(6), R989–R1001.
    [Google Scholar]
  12. Ovcharenko, O., Kazei, V., Plotnitskiy, P., Peter, D., Silvestrov, I., Bakulin, A. and Alkhalifah, T.
    [2020] Extrapolating low-frequency prestack land data with deep learning. In: SEG Technical Program Expanded Abstracts 2020, Society of Exploration Geophysicists, 1546–1550.
    [Google Scholar]
  13. Plotnitskii, P., Kazei, V., Ovcharenko, O., Peter, D. and Alkhalifah, T.
    [2020] Extrapolation of Low Wavenumbers in FWI Gradients by a Deep Convolutional Neural Network. In: 82nd EAGE Annual Conference & Exhibition, 2020. European Association of Geoscientists & Engineers, 1–5.
    [Google Scholar]
  14. Ronneberger, O., Fischer, P. and Brox, T.
    [2015] U-Net: Convolutional Networks for Biomedical Image Segmentation. ArXiv, abs/1505.04597.
    [Google Scholar]
  15. Soubaras, R. and Dowle, R.
    [2010] Variable-depth streamer-a broadband marine solution. Variable-depth streamer-a broadband marine solution., 28(12).
    [Google Scholar]
  16. Sun, H. and Demanet, L.
    [2019] Extrapolated full waveform inversion with deep learning. arXiv preprint arXiv:1909.11536.
    [Google Scholar]
  17. [2020] Deep learning for low frequency extrapolation of multicomponent data in elastic full waveform inversion. arXiv preprint arXiv:2101.00099.
    [Google Scholar]
  18. Wang, M., Xu, S. and Zhou, H.
    [2020] Self-supervised learning for low frequency extension of seismic data. In: SEG Technical Program Expanded Abstracts 2020, Society of Exploration Geophysicists, 1501–1505.
    [Google Scholar]
/content/papers/10.3997/2214-4609.202112949
Loading
/content/papers/10.3997/2214-4609.202112949
Loading

Data & Media loading...

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