1887
  1. Home
  2. A-Z Publications
  3. First Break
  4. Volume 40, Issue 12
  5. Article
Volume 40, Issue 12
  • ISSN: 0263-5046
  • E-ISSN: 1365-2397

Abstract

Summary

Removing noise present in seismic data is of prime importance for seismic processing workflows and a matter of continuous research in the academic community. The challenging part of seismic noise suppression is the diverse nature of seismic noise: it is found as a combination of random and coloured noise, which can be both structured and unstructured. Algorithms based on signal decomposition, domain transformation, and filtering, among others, have been traditionally applied to denoise seismic data and have been successful for specific imaging targets, hence mostly identifying a specific seismic noise component. Recently, convolutional neural networks-based (CNN) denoisers have greatly outperformed standard denoising techniques mostly in natural and medical imaging applications, and furthermore, self-supervised frameworks have been proposed as a clever alternative to denoising when no ground truth exists. This work leverages four state-of-the-art U-Net type architectures in a novel self-supervised fashion to remove seismic noise. The training seismic data corresponds to a generous number of real seismic surveys. For the labelling, trace-wise corruption is applied to patches of the input data, so the CNN learns to predict the corrupted traces based on the receptive field. Our findings indicate that self-supervised learning using U-Net type architecture trained on real data is able to considerably remove both structured and unstructured seismic noise.

EAGE Publications BV
Loading

Article metrics loading...

/content/journals/10.3997/1365-2397.fb2022104
2022-12-01
2024-04-25

  • From This Site

    /content/journals/10.3997/1365-2397.fb2022104
    dcterms_title,dcterms_subject,pub_keyword
    -contentType:Journal -contentType:Contributor -contentType:Concept -contentType:Institution
    10
    5
Loading full text...

Full text loading...

References

  1. Alom, M.Z., Hasan, M., Yakopcic, C., Taha, T. M. and Asari, V.K. [2018]. Recurrent residual convolutional neural network based on u-net (r2u-net) for medical image segmentation.CoRR, abs/1802.06955, 2018. URL http://arxiv.org/abs/1802.06955.
     [Google Scholar]
  2. Birnie, C., Ravasi, M., Alkhalifah, T. and Liu, S. [2021]. The potential of self-supervised networks for randomnoise suppression in seismic data. doi: 10.48550/ARXIV.2109.07344. URL https://arxiv.org/abs/2109.07344.
     https://doi.org/10.48550/ARXIV.2109.07344 [Google Scholar]
  3. Broaddus, C., Krull, A., Weigert, M., Schmidt, U. and Myers, G. [2020]. Removing structured noise with self- supervised blind-spot networks. pages 159-16. doi: 10.1109/ISBI45749.2020.9098336.
     https://doi.org/10.1109/ISBI45749.2020.9098336 [Google Scholar]
  4. Huang, H., Lin, L., Tong, R., Hu, H., Zhang, Q., Iwamoto, Y., Han, X., Chen, Y.-W. and Wu, J. [2020]. Unet 3+: A full-scale connected UNet for medical image segmentation. doi: 10.48550/ARXIV.2004.08790. URL https://arxiv.org/abs/2004.08790.
     https://doi.org/10.48550/ARXIV.2004.08790 [Google Scholar]
  5. Krull, A., Buchholz, T.-O. and Jug, F. [2018]. Noise2void - learning denoising from single noisy images. doi: 10.48550/ARXIV.1811.10980. URL https://arxiv.org/abs/1811.10980.
     https://doi.org/10.48550/ARXIV.1811.10980 [Google Scholar]
  6. Lehtinen, J., Munkberg, J., Hasselgren, J., Laine, S., Karras, T., Aittala, M. and Aila, T. [2018]. Noise2noise: Learning image restoration without clean data. 2018. doi: 10.48550/ARXIV.1803.04189. URL https://arxiv.org/abs/1803.04189.
     https://doi.org/10.48550/ARXIV.1803.04189 [Google Scholar]
  7. Liu, S., Birnie, C. and Alkhalifah, T. [2022]. Coherent noise suppression via a self-supervised blind-trace deep learning scheme. doi: 10.48550/ARXIV.2206.00301. URL https://arxiv.org/abs/2206.00301.
     https://doi.org/10.48550/ARXIV.2206.00301 [Google Scholar]
  8. Mosser, L., Kuha, A., Lettmann, A. and Heredsvela, J. [2022]. Deep learning-based unsupervised denoising for coherent noise attenuation in seismic data. SEG-IMAGE 22 Expanded Abstracts, 2022.
     [Google Scholar]
  9. Oktay, O., Schlemper, J., Folgoc, L.L., Lee, M.C.H., Heinrich, M.P., Misawa, K., Mori, K., McDonagh, S.G., Hammerla, N.Y., Kainz, B., Glocker, B. and Rueckert, D. [2018]. Attention u-net: Learning where to look for the pancreas.CoRR, abs/1804.03999, 2018. URL http://arxiv.org/abs/1804.03999.
     [Google Scholar]
  10. Ronneberger, O., Fischer, P. and Brox, T. [2015].U-net: Convolutional networks for biomedical image segmentation.CoRR, abs/1505.04597. URL http://arxiv.org/abs/1505.04597.
     [Google Scholar]
  11. Zhang, K., Zuo, W., Chen, Y., Meng, D. and Zhang, L. [2017]. Beyond a gaussian denoiser: Residual learning of deep cnn for image denoising.IEEE transactions on image processing, 26(7), 3142–3155.
     [Google Scholar]
http://instance.metastore.ingenta.com/content/journals/10.3997/1365-2397.fb2022104
Loading
A Novel Approach to Train Self-Supervised Seismic Denoising Dnn Architectures
First Break 40, 71 (2022); https://doi.org/10.3997/1365-2397.fb2022104
/content/journals/10.3997/1365-2397.fb2022104
/content/journals/10.3997/1365-2397.fb2022104
Loading

Data & Media loading...

  • Article Type: Research Article

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