1887

Abstract

Summary

Subsurface seismic imaging is essential for exploration and reservoir assessment, but it often has poor resolution because of acquisition technologies imperfection, geological complexities, and noise presence. Traditional enhancement methods are ineffective due to mathematical constraints, on the other hand data-driven approaches offer more flexibility. This study presents a deep learning-based seismic image enhancement algorithm based on modified U-Net architecture trained on specifically generated synthetic data. The broad variety of generated synthetics capture the intricate patterns of the field and completely mimic its geological and stratigraphic features. The proposed methodology requires no well data, no manual adjustment and ensures uniform improvements throughout the whole field. Tests of the proposed algorithm application on the real-field data confirm its effectiveness in enhancing resolution and enabling more accurate geological interpretations.

© EAGE Publications BV
Loading

Article metrics loading...

/content/papers/10.3997/2214-4609.202539082
2025-03-24
2026-02-15

  • From This Site

    /content/papers/10.3997/2214-4609.202539082
    dcterms_title,dcterms_subject,pub_keyword
    -contentType:Journal -contentType:Contributor -contentType:Concept -contentType:Institution
    10
    5
Loading full text...

Full text loading...

References

  1. Blache-Fraser, G., & Neep, J. [2004]. Increasing seismic resolution using spectral blueing and colored inversion: Cannonball field, Trinidad. SEG Technical Program Expanded Abstracts2004.
     [Google Scholar]
  2. Brown, A. R. [2011]. Interpretation of Three-Dimensional Seismic Data. American Association of Petroleum Geologists.
     [Google Scholar]
  3. Lancaster, S., and Whitcombe, D. [2000]. Fast-track ‘coloured’ inversion. SEG, 1572–1575.
     [Google Scholar]
  4. Lim, B., Son, S., Kim, H., Nah, S., & Mu Lee, K. [2017]. Enhanced deep residual networks for single image super-resolution. In Proceedings of the IEEE conference on computer vision and pattern recognition workshops.
     [Google Scholar]
  5. Ronneberger, O., Fischer, P. and Brox, T. [2015] U-net: Convolutional Networks for Biomedical Image Segmentation. In: International Conference on Medical Image Computing and Computer-Assisted Intervention, Springer, Cham, 234–241.
     [Google Scholar]
  6. Wu, X., Geng, Z., Shi, Y., Pham, N., Fomel, S., & Caumon, G. [2020]. Building realistic structure models to train convolutional neural networks for seismic structural interpretation. In GEOPHYSICS (Vol. 85, Issue 4, pp. WA27–WA39). Society of Exploration Geophysicists.
     [Google Scholar]
  7. Yilmaz, O., [2001]. Seismic data analysis: SEG.
     [Google Scholar]
/content/papers/10.3997/2214-4609.202539082
Loading
Integrating Deep Learning Methods in Seismic Image Resolution Enhancement
Conference Proceedings 2025, 1 (2025); https://doi.org/10.3997/2214-4609.202539082
/content/papers/10.3997/2214-4609.202539082
/content/papers/10.3997/2214-4609.202539082
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