1887
  1. Home
  2. Conferences
  3. Conference Proceedings
  4. 82nd EAGE Annual Conference & Exhibition
  5. Conference paper

Abstract

Summary

Convolutional based deep neural networks can be used in addition to existing workflows, to improve turnaround or as a ‘guide’ for further processing. Whilst a lot of effort has been made to try to improve the DNN architecture for processing tasks or to understand their physical interpretation, the choice of the training-set is rarely discussed. For a good quality DNN result, the training-set must be representative of the variability (or statistical diversity) of the full dataset, and the question of the choice of this dataset for seismic data is discussed in this paper. We present two methods for the selection of the training set. The first one is based on proxy attributes and their clustering. Our clustering approach is not only using the clusters themselves but also the information on the distance to the centroid for the cluster definition. The other method is based on the data themselves. It starts from a predefined training set and then scans through the full dataset to identify additional training points that will be used to augment the initial training set.

© EAGE Publications BV
Loading

Article metrics loading...

/content/papers/10.3997/2214-4609.202112817
2021-10-18
2024-04-20

  • From This Site

    /content/papers/10.3997/2214-4609.202112817
    dcterms_title,dcterms_subject,pub_keyword
    -contentType:Journal -contentType:Contributor -contentType:Concept -contentType:Institution
    10
    5
Loading full text...

Full text loading...

References

  1. Chambefort, M. and J.Messud
    [2020] Building and understanding deep neural network components for seismic processing: lessons learned, 82nd EAGE Conference & Exhibition Workshop Programme.
     [Google Scholar]
  2. Mandelli, S., Lipari, V., Bestagini, P.
    [2019] Interpolation and Denoising of Seismic Data using Convolutional Neural Networks. arXiv:1901.07927v4.
     [Google Scholar]
  3. Masclet, S., T.Bardainne, V.Massart and H.Prigent
    [2019] Near surface characterization in Southern Oman: Multi-Wave Inversion by Machine Learning, 81st EAGE Conference & Exhibition, Expanded Abstracts.
     [Google Scholar]
  4. Messud, J. and M.Chambefort
    [2020] Understanding how a deep neural network architecture choice can be related to a seismic processing task, First EAGE Digitalization Conference and Exhibition.
     [Google Scholar]
  5. Peng, H., Messud, J., Salaun, N., Hammoud, I., Jeunesse, P., Lesieur, T. and C.Lacombe
    [2021] DUnet architecture for seismic processing tasks - Proposal and theoretical analysis, 83rd EAGE Conference & Exhibition, Submitted.
     [Google Scholar]
  6. Richardson, A. and C.Feller
    [2019] Seismic data denoising and deblending using DL, arXiv:1907.01497
     [Google Scholar]
  7. Sun, H. and L.Demanet
    , [2018] Low frequency extrapolation with deep learning. SEG Technical Program Expanded Abstracts, 2011-2015.
     [Google Scholar]
  8. Hou, S. and H.Hoeber
    [2020] Seismic processing with deep convolutional neural network; opportunities and challenges, 82nd EAGE Conference & Exhibition, Expanded Abstracts.
     [Google Scholar]
  9. Vinje, V., Lie, J.E., Danielsen, V., Dhelie, P.E., Siliqi, R., Nilsen, C.I., Hicks, E. and A.Camerer
    [2017] Shooting over the seismic spread, First Break, vol 35, pp 97–104
     [Google Scholar]
  10. Wang, P., Ray, S., Peng, C., Li, Y., and G.Poole
    [2013] Premigration deghosting for marine streamer data using a bootstrap approach in tau-p domain, SEG Technical Program Expanded Abstracts, 4221–4225.
     [Google Scholar]
http://instance.metastore.ingenta.com/content/papers/10.3997/2214-4609.202112817
Loading
Data-driven method for training data selection for deep learning
Conference Proceedings 2021, 1 (2021); https://doi.org/10.3997/2214-4609.202112817
/content/papers/10.3997/2214-4609.202112817
/content/papers/10.3997/2214-4609.202112817
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