1887
  1. Home
  2. A-Z Publications
  3. Geophysical Prospecting
  4. Volume 68, Issue 3
  5. Article
Volume 68, Issue 3
  • E-ISSN: 1365-2478

Abstract

ABSTRACT

Marine seismic interference noise occurs when energy from nearby marine seismic source vessels is recorded during a seismic survey. Such noise tends to be well preserved over large distances and causes coherent artefacts in the recorded data. Over the years, the industry has developed various denoising techniques for seismic interference removal, but although well performing, they are still time‐consuming in use. Machine‐learning‐based processing represents an alternative approach, which may significantly improve the computational efficiency. In the case of conventional images, autoencoders are frequently employed for denoising purposes. However, due to the special characteristics of seismic data as well as the noise, autoencoders failed in the case of marine seismic interference noise. We, therefore, propose the use of a customized U‐Net design with element‐wise summation as part of the skip‐connection blocks to handle the vanishing gradient problem and to ensure information fusion between high‐ and low‐level features. To secure a realistic study, only seismic field data were employed, including 25,000 training examples. The customized U‐Net was found to perform well, leaving only minor residuals, except for the case when seismic interference noise comes from the side. We further demonstrate that such noise can be treated by slightly increasing the depth of our network. Although our customized U‐Net does not outperform a standard commercial algorithm in quality, it can (after proper training) read and process one single shot gather in approximately 0.02 s. This is significantly faster than any existing industry denoising algorithm. In addition, the proposed network processes shot gathers in a sequential order, which is an advantage compared with industry algorithms that typically require a multi‐shot input to break the coherency of the noise.

© 2020 European Association of Geoscientists & Engineers © 2019 European Association of Geoscientists & Engineers
Loading

Article metrics loading...

/content/journals/10.1111/1365-2478.12893
2020-01-19
2024-04-23

  • From This Site

    /content/journals/10.1111/1365-2478.12893
    dcterms_title,dcterms_subject,pub_keyword
    -contentType:Journal -contentType:Contributor -contentType:Concept -contentType:Institution
    10
    5
Loading full text...

Full text loading...

References

  1. AbadiM., BarhamP., ChenJ., ChenZ., DavisA., DeanJ., et al. 2016. Tensorflow: a system for large‐scale machine learning. Proceedings of the 12th USENIX Symposium on Operating Systems Design and Implementation, Savannah, GA, USA, 265–283.
  2. AkbulutK., SaelandO., FarmerP. and CurtisT.1984. Suppression of seismic interference noise on Gulf of Mexico data. 54th SEG Annual Meeting, Atlanta, USA, Expanded Abstracts, 527–529.
  3. BaardmanR.2018. Classification and suppression of blending noise using CNN. First EAGE/PESGB Workshop Machine Learning, London, UK, Extended Abstracts, ML 11.
  4. BaardmanR. and TsingasC.2019. Classification and suppression of blending noise using convolutional neural networks. SPE Middle East Oil and Gas Show and Conference, Manama, Bahrain, Conference Papers, SPE‐194731‐MS.
  5. DengL. and YuD.2014. Deep learning: methods and applications. Foundations and Trends in Signal Processing7, 197–387.
     [Google Scholar]
  6. DumoulinV. and VisinF.2018. A guide to convolution arithmetic for deep learning. arXiv, 1603.07285.
  7. ElbothT., PresterudI.V. and HermansenD.2010. Time‐frequency seismic data de‐noising. Geophysical Prospecting58, 441–453.
     [Google Scholar]
  8. FukushimaK.2007. Neocognitron. Scholarpedia2, 1717.
     [Google Scholar]
  9. GondaraL.2016. Medical image denoising using convolutional denoising autoencoders. 16th IEEE International Conference on Data Mining Workshops (ICDMW), Barcelona, Spain, Extended Abstracts, 241–246.
  10. GoodfellowI., BengioY. and CourvilleA.2016. Deep Learning. MIT press.
     [Google Scholar]
  11. GulunayN.2008. Two different algorithms for seismic interference noise attenuation. The Leading Edge27, 176–181.
     [Google Scholar]
  12. GulunayN., MagesanM. and BaldockS.2004. Seismic interference noise attenuation. 74th SEG Technical Program, Denver, Colorado, US, Expanded Abstracts, 1973–1976.
  13. GulunayN. and PattbergD.2001a. Seismic crew interference and prestack random noise attenuation on 3‐D marine seismic data. 63rd EAGE Conference and Exhibition, Amsterdam, The Netherlands, Extended Abstracts, A‐13.
  14. GulunayN. and PattbergD.2001b. Seismic interference noise removal. 71st SEG Meeting, San Antonio, Texas, US, Expanded Abstracts, 1989–1992.
  15. GuoJ. and LinD.2003. High‐amplitude noise attenuation. 73rd SEG Meeting, Dallas, Texas, US, Expanded Abstracts, 1893–1896.
  16. GwardysG.2016. Convolutional neural networks backpropagation: from intuition to derivation.
  17. HeK., ZhangX., RenS. and SunJ.2016. Deep residual learning for image recognition. Proceedings of the 29th IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA, 770–778.
  18. HubelD.H. and WieselT.N.1968. Receptive fields and functional architecture of monkey striate cortex. The Journal of Physiology195, 215–243.
     [Google Scholar]
  19. JansenS., ElbothT. and SanchisC.2013. Two seismic interference attenuation methods based on automatic detection of seismic interference moveout. 75th EAGE Annual Meeting, London, UK, Extended Abstracts, We 14 15.
  20. KommedalJ.H., SembP.H. and ManningT.2007. A case of SI attenuation in 4D seismic data recorded with a permanently installed array. Geophysics72, Q11–Q14.
     [Google Scholar]
  21. LaurainR., Ruiz‐LopezF. and EidsvigS.2014. Improving acquisition efficiency by managing and modelling seismic interference. First Break32, 79–85.
     [Google Scholar]
  22. LiF.‐F., JohnsonJ. and YoungS.2017. Lecture 11: detection and segmentation. CS231n: Convolutional Neural Networks for Visual Recognition, Stanford.
  23. LiuD., WangW., ChenW., WangX., ZhouY. and ShiZ.2018. Random noise suppression in seismic data: what can deep learning do?. 88th SEG Meeting, Anaheim, CA, US, Expanded Abstracts, 2016–2020.
  24. MaJ.2018. Deep learning for attenuating random and coherence noise simultaneously. 80th EAGE International Conference and Exhibition, Copenhagen, Denmark, Extended Abstracts, Tu P7 07.
  25. MaasA.L., HannunA.Y. and NgA.Y.2013. Rectifier nonlinearities improve neural network acoustic models. Proceedings of the 30th International Conference on Machine Learning, Atlanta, US, 3.
  26. MandelliS., BorraF., LipariV., BestaginiP., SartiA. and TubaroS.2018. Seismic data interpolation through convolutional autoencoder. 88th SEG Meeting, Anaheim, CA, US, Expanded Abstracts, 4101–4105.
  27. MandelliS., LipariV., BestaginiP. and TubaroS.2019. Interpolation and denoising of seismic data using convolutional neural networks. arXiv, 1901.07927.
  28. MatsuguM., MoriK., MitariY. and KanedaY.2003. Subject independent facial expression recognition with robust face detection using a convolutional neural network. Neural Networks16, 555–559.
     [Google Scholar]
  29. MehtaP., BukovM., WangC.H., DayA.G.R., RichardsonC., FisherC.K., et al. 2019. A high‐bias, low‐variance introduction to machine learning for physicists. Physics Reports, 810, 1–124.
     [Google Scholar]
  30. MitchellT.M.1997. Machine Learning. McGraw‐Hill Higher Education.
     [Google Scholar]
  31. PaszkeA., GrossS., ChintalaS., ChananG., YangE., DeVitoZ., et al. 2017. Automatic differentiation in PyTorch. 31st Conference on Neural Information Processing Systems, Long Beach, California, USA.
  32. QianF., YinM., LiuX.Y., WangY.J., LiuC. and HuG.M.2018. Unsupervised seismic facies analysis via deep convolutional autoencoders. Geophysics83, A39–A43.
     [Google Scholar]
  33. RentschS., HolickiM.E., KamilY.I., RobertssonJ.O.A. and VassalloM.2014. How to teach a neural network to identify seismic interference. 76th EAGE Conference and Exhibition, Amsterdam, The Netherlands, Extended Abstracts, Th ELI1 07.
  34. RonnebergerO., FischerP. and BroxT.2015. U‐net: Convolutional networks for biomedical image segmentation. Springer International Conference on Medical image computing and computer‐assisted intervention, Cham, Conference Papers, 234–241.
  35. ShenH., ElbothT., TaoC., TianG., WangH., QiuL. and ZhouJ.2019. Using data regrouping methods to attenuate shot‐to‐shot coherent interference noise in marine seismic data. Earth and Space Science6.
     [Google Scholar]
  36. SlangS., SunJ., ElbothT., McDonaldS. and GeliusL.J.2019. Using convolutional neural networks for denoising and deblending of marine seismic data. 81st EAGE Conference and Exhibition, London, UK, Extended Abstracts, Tu R06 05.
  37. TielemanT. and HintonG.2012. Divide the gradient by a running average of its recent magnitude: COURSERA. Neural networks for machine learning 4.2, 26–31.
     [Google Scholar]
  38. WaldelandA.U., JensenA.C., GeliusL.J. and SolbergA.H.S.2018. Convolutional neural networks for automated seismic interpretation. The Leading Edge37, 529–537.
     [Google Scholar]
  39. WangB.F., ZhangN., LuW.K., ZhangP. and GengJ.H.2018a. Seismic data interpolation using deep learning based residual networks. 80th EAGE Conference and Exhibition, Copenhagen, Denmark, Extended Abstracts, Th A15 14.
  40. WangB.F., ZhangN., LuW.K. and WangJ.2018b. Deep learning‐based seismic data interpolation: a preliminary result. Geophysics84, V11‐V20.
     [Google Scholar]
  41. WangH., LiuG., HinzC.E. and SnyderF.F.C.1989. Attenuation of marine coherent noise. 59th SEG Annual Meeting, Dallas, Texas, US, Expanded Abstracts, 1112–1114.
  42. WillmottC.J. and MatsuuraK.2005. Advantages of the mean absolute error (MAE) over the root mean square error (RMSE) in assessing average model performance. Climate Research30, 79–82.
     [Google Scholar]
  43. WuH., ZhangB., LiF. and LiuN.2019. Semi‐automatic first arrival picking of micro‐seismic events by using pixel‐wise convolutional image segmentation method. Geophysics84, V143–V155.
     [Google Scholar]
  44. XieJ., XuL. and ChenE.2012. Image denoising and inpainting with deep neural networks. Advances in Neural Information Processing Systems25, 341–349.
     [Google Scholar]
  45. XiongW., JiX., MaY., WangY., AlBinHassanN.M., AliM.N., et al. 2018. Seismic fault detection with convolutional neural network. Geophysics83, O97–O103.
     [Google Scholar]
  46. ZhangZ. and WangP.2015. Seismic interference noise attenuation based on sparse inversion. 85th SEG Annual Meeting, New Orleans, Louisiana, US, Expanded Abstracts, 4662–4666.
http://instance.metastore.ingenta.com/content/journals/10.1111/1365-2478.12893
Loading
Attenuation of marine seismic interference noise employing a customized U‐Net
Geophysical Prospecting 68, 845 (2020); https://doi.org/10.1111/1365-2478.12893
/content/journals/10.1111/1365-2478.12893
/content/journals/10.1111/1365-2478.12893
Loading

Data & Media loading...

  • Article Type: Research Article
Keyword(s): Attenuation; Noise; Seismics; Signal processing

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