1887

Abstract

Summary

Representing seismic data effectively for facies categorization poses a challenge. In order to account for all information presented in prestack seismic data for this task, a machine learning model based on Deep Convolutional Autoencoders (DCAE) combined with a K-means clustering to identify seismic facies in a Brazilian pre-Salt layer is utilized. The DCAE reduces the dimensionality of the prestack seismic data by non-linear means, and the resulting latent features are used for K-means clustering. To incorporate geological interpretation, the thickness of the layer of interest was considered when defining the input window for each gather based on the interpreted top and bottom horizons. The results demonstrate through principal component analysis in the latent features that the layer thickness information drives the main behavior of the samples in the study area. Moreover, it is pointed out that considering the layer thickness leads to vertical stretching and squeezing in the input features, influencing the pattern recognition by the DCAE. Nevertheless, the embedding of geological interpretation through layer boundaries generated helpful facies distribution results for assembling the geological model of the reservoir.

© EAGE Publications BV
Loading

Article metrics loading...

/content/papers/10.3997/2214-4609.202510771
2025-06-02
2026-02-08

  • From This Site

    /content/papers/10.3997/2214-4609.202510771
    dcterms_title,dcterms_subject,pub_keyword
    -contentType:Journal -contentType:Contributor -contentType:Concept -contentType:Institution
    10
    5
Loading full text...

Full text loading...

References

  1. Kourki, M. and Riahi, M.A. [2014] Seismic facies analysis from pre-stack data using self-organizing maps. Journal of Geophysics and Engineering, 11, 065005.
     [Google Scholar]
  2. Matos, M.C., Osorio, P.L. and Johann, P.R. [2007] Unsupervised seismic facies analysis using wavelet transform and self-organizing maps. Geophysics, 72, P9–P21.
     [Google Scholar]
  3. Qian, E., Yin, M., Liu, X.Y., Wang, Y.J., Lu, C. and Hu, G.M. [2018] Unsupervised seismic facies analysis via deep convolutional autoencoders. Geophysics, 83, A39–A43.
     [Google Scholar]
  4. Roden, R., Smith, T. and Sacrey, D. [2015] Geologic pattern recognition from seismic attributes: Principal component analysis and self-organizing maps. Interpretation, 3, SAE59–SAE83.
     [Google Scholar]
  5. Saraswat, P. and Sen, M.K. [2012] Artificial immune-based self-organizing maps for seismic-facies analysis. Geophysics, 77, O45–O53.
     [Google Scholar]
  6. Silvany, P.H.S., Machado, M., Matos, M. and Paes, M. [2021] Joint multiazimuthal prestack and time-frequency attributes seismic facies prediction via deep learning: An application to a Brazilian presalt reservoir. In: First International Meeting for Applied Geoscience & Energy Expanded Abstracts, 2021-September. Society of Exploration Geophysicists, 1480–1484.
     [Google Scholar]
  7. Wei, Y and Zhang, Q. [2000] Common Waveform Analysis, 9. Springer US.
     [Google Scholar]
  8. Zhao, T., Jayaram, V., Roy, A. and Marfurt, K.J. [2015] A comparison of classification techniques for seismic facies recognition. Interpretation, 3, SAE29–SAE58.
     [Google Scholar]
/content/papers/10.3997/2214-4609.202510771
Loading
Deep Learning and Layer Thickness Information for Seismic Facies Analysis in a Brazilian pre-Salt Reservoir
Conference Proceedings 2025, 1 (2025); https://doi.org/10.3997/2214-4609.202510771
/content/papers/10.3997/2214-4609.202510771
/content/papers/10.3997/2214-4609.202510771
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