1887

Abstract

Summary

Seismic data contains valuable information about the subsurface, but also contains noise that can be distracting. Denoising is an important step in seismic data processing. We used a U-Net-shaped encoder-decoder network with ResNeXt blocks and added self-attention to the deeper layers of the network. Additionally, we implemented attention gates as a second mechanism in order to attend to global features next to the local ones. We evaluated the impact of attention on machine-learning-based processing of seismic data by comparing results obtained without attention, with single attention, and dual attention. The results indicated that dual attention yielded improved denoising results compared to single attention, and single attention produced better results than without attention. Our proposed method resulted therefore in better preservation of the desired seismic signal.

© EAGE Publications BV
Loading

Article metrics loading...

/content/papers/10.3997/2214-4609.2023101077
2023-06-05
2026-04-15

  • From This Site

    /content/papers/10.3997/2214-4609.2023101077
    dcterms_title,dcterms_subject,pub_keyword
    -contentType:Journal -contentType:Contributor -contentType:Concept -contentType:Institution
    10
    5
Loading full text...

Full text loading...

References

  1. Bello, I., B.Zoph, A.Vaswani, J.Shlens, and Q. V.Le. [2019] Attention augmented convolutional networks. CoRR, abs/1904.09925.
     [Google Scholar]
  2. Dou, Y., K.Li, J.Zhu, X.Li, and Y.Xi. [2021] Seismic fault segmentation via 3d-cnn training by a few 2d slices labels. CoRR, abs/2105.03857.
     [Google Scholar]
  3. Knispel, S., J.Walda, R.Zehn, A.Bauer, and D.Gajewski. [2022] A self-attention enhanced encoder-decoder network for seismic data denoising. IMAGE Conference 2022, Extended Abstracts.
     [Google Scholar]
  4. Ruempker, H.Stoecker, and N.Srivastava. [2021] Epick: Multi-class attention-based u-shaped neural network for earthquake detection and seismic phase picking. ArXiV, abs/2109.02567.
     [Google Scholar]
  5. Mandelli, S., V.Lipari, P.Bestagini, and S.Tubaro. [2019] Interpolation and denoising of seismic data using convolutional neural networks. ArXiV, abs/1901.07927.
     [Google Scholar]
  6. Oktay, O., J.Schlemper, L. L.Folgoc, M. C. H.Lee, M. P.Heinrich, K.Misawa, K.Mori, S. G.McDonagh, N. Y.Hammerla, B.Kainz, B.Glocker, and D.Rueckert. [2018] Attention u-net: Learning where to look for the pancreas. CoRR, abs/1804.03999.
     [Google Scholar]
  7. Ronneberger, O., P.Fischer, and T.Brox. [2015] U-net: Convolutional networks for biomedical image segmentation. ArXiV, abs/1505.04597.
     [Google Scholar]
  8. Trickett, S., and L.Burroughs. [2009] Prestack rank-reduction based noise suppression: Theory. Recorder, 34.
     [Google Scholar]
  9. Vaswani, A., N.Shazeer, N.Parmar, J.Uszkoreit, L.Jones, A. N.Gomez, L.Kaiser, and I.Polosukhin. [2017] Attention is all you need. CoRR, abs/1706.03762.
     [Google Scholar]
  10. Walda, J., and D.Gajewski. [2021] Early-stage noise removel using a convolutional autoencoder. 82nd EAGE Annual Conference and Exhibition, 2021, Extended Abstracts, 1–5.
     [Google Scholar]
  11. Wang, Z., A. C.Bovik, H. R.Sheikh, and E. P.Simoncelli. [2004] Image quality assessment: from error visibility to structural similarity. IEEE Transactions on Image Processing, 13, 600–612.
     [Google Scholar]
  12. Xie, S., R. B.Girshick, P.Dollar, Z.Tu, and K.He. [2016] Aggregated residual transformations for deep neural networks. CoRR, abs/1611.05431.
     [Google Scholar]
/content/papers/10.3997/2214-4609.2023101077
Loading
A Dual Attention Enhanced Encoder-Decoder Network for Seismic Data Denoising
Conference Proceedings 2023, 1 (2023); https://doi.org/10.3997/2214-4609.2023101077
/content/papers/10.3997/2214-4609.2023101077
/content/papers/10.3997/2214-4609.2023101077
Loading

Data & Media loading...

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