1887

Abstract

Summary

In this work we explore deep metric learning as a data-driven approach for segmentation of first-order stratigraphic units in 3D seismic, based on similarities in reflection patterns. We attempt to learn similarity in seismic reflection patterns from a set of general synthetic seismic classes defined in our modelling pipeline. We use synthetics to 1) avoid using manual labels, with their limitations and 2) by using synthetics rather than samples from a specific seismic survey in training, we hope to achieve a more generalizable model that can be applied on multiple surveys without the need for fine-tuning or retraining. Using the N-pair multiclass loss we train a 3D CNN to embed the input such that the distance between positive pairs sampled from the same synthetic class in the features space is minimized, while the distance to the negative pairs is maximized.

To introduce the positional context of each prediction we use a pseudo-RGT volume calculated from the unwrapped phase image in 3D of the input seismic, which is added as a weighted feature to the encoded feature vectors prior to clustering. Finally, the number of clusters must be determined before applying agglomerative clustering algorithm with Ward’s criterion and a connectivity constraint.

© EAGE Publications BV
Loading

Article metrics loading...

/content/papers/10.3997/2214-4609.2023101187
2023-06-05
2026-01-12

  • From This Site

    /content/papers/10.3997/2214-4609.2023101187
    dcterms_title,dcterms_subject,pub_keyword
    -contentType:Journal -contentType:Contributor -contentType:Concept -contentType:Institution
    10
    5
Loading full text...

Full text loading...

References

  1. Coléou, T., Poupon, M., & Azbel, K. (2003). Unsupervised seismic facies classification: A review and comparison of techniques and implementation. The Leading Edge, 22(10), 942–953. https://doi.org/10.1190/1.1623635
     [Google Scholar]
  2. Dramsch, J. S., & Lüthje, M. (2018). Deep-learning seismic facies on state-of-the-art CNN architectures. figshare.
     [Google Scholar]
  3. Gao Hang, G. H., Wu Xinming, W. X., & Liu Guofeng, L. G. (2021). ChannelSeg3D; channel simulation and deep learning for channel interpretation in 3D seismic images. Geophysics, 86(4), IM73–IM83.
     [Google Scholar]
  4. Geng, Z., Wu, X., Shi, Y., & Fomel, S. (2020). Deep learning for relative geologic time and seismic horizons. GEOPHYSICS, 85(4), WA87–WA100. https://doi.org/10.1190/geo2019-0252.1
     [Google Scholar]
  5. Kaur, H., Pham, N., Fomel, S., Geng, Z., Decker, L., Gremillion, B., Jervis, M., Abma, R., & Gao, S. (2021). A deep learning framework for seismic facies classification. In First International Meeting for Applied Geoscience & Energy Expanded Abstracts (pp. 1420–1424). https://doi.org/10.1190/segam2021-3583072.1
     [Google Scholar]
  6. Kokilepersaud, K., Prabhushankar, M., & AlRegib, G. (2022). Volumetric supervised contrastive learning for seismic semantic segmentation. In Second International Meeting for Applied Geoscience & Energy (pp. 1699–1703). https://doi.org/10.1190/image2022-3751735.1
     [Google Scholar]
  7. Li, J., Wu, X., Ye, Y., Yang, C., Hu, Z., Sun, X., & Zhao, T. (2023). Unsupervised contrastive learning for seismic facies characterization. GEOPHYSICS, 88(1), WA81–WA89. https://doi.org/10.1190/geo2022-0148.1
     [Google Scholar]
  8. Mitchum, R. M., Jr., Vail, P. R., & Sangree, J. B. (1977). Seismic Stratigraphy and Global Changes of Sea Level, Part 6: Stratigraphic Interpretation of Seismic Reflection Patterns in Depositional Sequences1. In C. E.Payton (Ed.), Seismic Stratigraphy—Applications to Hydrocarbon Exploration (Vol. 26, p. 0). American Association of Petroleum Geologists. https://doi.org/10.1306/M26490C8
     [Google Scholar]
  9. Puzyrev, V., & Elders, C.(2022). Unsupervised seismic facies classification using deep convolutional autoencoder. Geophysics, 87(4), IM125–IM132.
     [Google Scholar]
  10. Qian, F., Yin, M., Liu, X.-Y., Wang, Y.-J., Lu, C., & Hu, G.-M. (2018). Unsupervised seismic facies analysis via deep convolutional autoencoders. GEOPHYSICS, 83(3), A39–A43. https://doi.org/10.1190/geo2017-0524.1
     [Google Scholar]
  11. Sohn, K. (2016). Improved Deep Metric Learning with Multi-class N-pair Loss Objective. In D.Lee, M.Sugiyama, U.Luxburg, I.Guyon, & R.Garnett (Eds.), Advances in Neural Information Processing Systems (Vol. 29). Curran Associates, Inc. https://proceedings.neurips.cc/paper/2016/file/6b180037abbebea991d8b1232f8a8ca9-Paper.pdf
     [Google Scholar]
  12. Wrona, T., Pan, I., Gawthorpe, R. L., & Fossen, H. (2018). Seismic facies analysis using machine learning. GEOPHYSICS, 83(5), O83–O95. https://doi.org/10.1190/geo2017-0595.1
     [Google Scholar]
  13. Wu, X., Liang, L., Shi, Y., & Fomel, S. (2019). FaultSeg3D: Using synthetic data sets to train an end-to-end convolutional neural network for 3D seismic fault segmentation. GEOPHYSICS, 84(3), IM35–IM45. https://doi.org/10.1190/geo2018-0646.1
     [Google Scholar]
/content/papers/10.3997/2214-4609.2023101187
Loading
Deep Metric Learning: Towards Extraction of First-order Stratigraphic Units in 3D Seismic
Conference Proceedings 2023, 1 (2023); https://doi.org/10.3997/2214-4609.2023101187
/content/papers/10.3997/2214-4609.2023101187
/content/papers/10.3997/2214-4609.2023101187
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