1887

Abstract

Summary

High-precision detection of geological anomalies could be achieved through diffractions generated when seismic or electromagnetic wave propagates in subsurface discontinuities. However, capturing the diffracted portions of the full wavefield from acquired seismic or ground penetrating radar data is challenging due to strong interference and waveform blending. The aforementioned factors contribute to difficulty in deploying robust diffraction extraction and imaging in various data domains. To enhance the accuracy of diffraction separation and imaging, we build anew intricate mapping from full wavefield in dip-angle domain common image gather (Dip-ADCIG) to unique migrated diffractions with deep learning technique. By virtue of the encoder-decoder framework, characteristics of diffracted wave can be depicted. Self-attention computation in the improved backbone ensures the coincident fidelity between input and result. Apart from the utilization of optimally configured encoder panel, mode of feature maps concatenating is modified in decoder module so as to obtain the diffraction imaging of small-scale heterogeneities. Through a stable training with synthetic data for diverse designed geological models, the new workflow can provide a high standard depth-domain imaging of diffractions even with poor quality input gathers. Numerical data tests verify the high performance and validity of our proposed method.

© EAGE Publications BV
Loading

Article metrics loading...

/content/papers/10.3997/2214-4609.202510485
2025-06-02
2026-02-09

  • From This Site

    /content/papers/10.3997/2214-4609.202510485
    dcterms_title,dcterms_subject,pub_keyword
    -contentType:Journal -contentType:Contributor -contentType:Concept -contentType:Institution
    10
    5
Loading full text...

Full text loading...

References

  1. Bauer, A., Schwarz, B., Walda, J. and Gajewski, D. [2023] Deep learning diffraction separation for seismic and GPR data. In: 84th Annual International Conference and Exhibition. EAGE, Extended Abstracts, 1–5.
     [Google Scholar]
  2. Chen, L.C., Zhu, Y., Papandreou, G., Schroff, F. and Adam, H. [2018] Encoder-decoder with atrous separable convolution for semantic image segmentation. In: Proceedings of the European conference on computer vision (ECCV). 801–818.
     [Google Scholar]
  3. Fomel, S., Landa, E. and Taner, M.T. [2007] Poststack velocity analysis by separation and imaging of seismic diffractions. Geophysics, 72(6), U89–U94.
     [Google Scholar]
  4. Klokov, A. and Fomel, S. [2012] Separation and imaging of seismic diffractions using migrated dipangle gathers. Geophysics, 77(6), S131–S143.
     [Google Scholar]
  5. Klokov, A. and Fomel, S. [2013] Selecting an optimal aperture in Kirchhoff migration using dip-angle images. Geophysics, 78(6), S243–S254.
     [Google Scholar]
  6. Landa, E., Fomel, S. and Reshef, M. [2008] Separation, imaging, and velocity analysis of seismic diffractions using migrated dip-angle gathers. In: 78th Annual International Meeting. SEG, Expanded Abstracts, 2176–2180.
     [Google Scholar]
  7. Liu, Z., Lin, Y., Cao, Y., Hu, H., Wei, Y., Zhang, Z., Lin, S. and Guo, B. [2021] Swin transformer: Hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE/CVF international conference on computer vision. 10012–10022.
     [Google Scholar]
  8. Lowney, B., Lokmer, I. and O'Brien, G.S. [2021] Multi-domain diffraction identification: A supervised deep learning technique for seismic diffraction classification. Computers & Geosciences, 155, 104845.
     [Google Scholar]
  9. Paffenholz, J., McLain, B., Zaske, J. and Keliher, P.J. [2002] Subsalt multiple attenuation and imaging: Observations from the Sigsbee2B synthetic dataset. In: 72nd Annual International Meeting. SEG, Expanded Abstracts, 2122–2125.
     [Google Scholar]
/content/papers/10.3997/2214-4609.202510485
Loading
Diffraction Wave Separation and Imaging by Encoder-Decoder Network Embedded Transformer
Conference Proceedings 2025, 1 (2025); https://doi.org/10.3997/2214-4609.202510485
/content/papers/10.3997/2214-4609.202510485
/content/papers/10.3997/2214-4609.202510485
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