1887

Abstract

Summary

In this paper, we propose a new method for automatic stacking velocity analysis, using AG-UNet3+ to construct deep neural network architecture to pick velocity spectrum. Compared with the conventional manual velocity spectrum picking method, our method is less affected by seismic noise, multiple waves, etc., and has better applicability under complex geological conditions. Compared with conventional deep learning methods, our neural network structure combines the full-scale skip connection and attention mechanism, which improves the generalization ability of the network and the ability to identify energy clusters in the velocity spectrum. The application results of actual seismic data show that our method can automatically pick up velocity spectrum in complex structural zones, and the precision of superimposed velocity field modeling is higher than that of conventional methods.

© EAGE Publications BV
Loading

Article metrics loading...

/content/papers/10.3997/2214-4609.202510492
2025-06-02
2026-02-08

  • From This Site

    /content/papers/10.3997/2214-4609.202510492
    dcterms_title,dcterms_subject,pub_keyword
    -contentType:Journal -contentType:Contributor -contentType:Concept -contentType:Institution
    10
    5
Loading full text...

Full text loading...

References

  1. WangW, McMechanG A, MaJet al., 2021, Automatic velocity picking from semblances with a new deep-learning regression strategy: Comparison with a classification approach. Geophysics, 86(2): U1–U13.
     [Google Scholar]
  2. Fabien-OuelletG, SarkarR, 2020, Seismic velocity estimation: A deep recurrent neural-network approach. Geophysics, 85(1): U21–U29.
     [Google Scholar]
  3. LeiteL W B, VieiraW W S, 2019, Automatic seismic velocity analysis based on nonlinear optimization of the semblance function. Journal of Applied Geophysics, 161: 182–192.
     [Google Scholar]
  4. HUANGH, LINL, TONGR, et al., 2020, UNet 3+: a full-scale connected unet for medical image segmentation. IEEE International Conference on Acoustics, Speech and Signal Processing: 1055–1059.
     [Google Scholar]
  5. OktayO, SchlemperJ, FolgocL Let al., 2018, Attention U-Net: Learning Where to Look for the Pancreas. Proceedings of the International Conference on Medical Imaging with Deep Learning.
     [Google Scholar]
/content/papers/10.3997/2214-4609.202510492
Loading
Research on Automatic Velocity Spectra Picking Using AG-UNet3+
Conference Proceedings 2025, 1 (2025); https://doi.org/10.3997/2214-4609.202510492
/content/papers/10.3997/2214-4609.202510492
/content/papers/10.3997/2214-4609.202510492
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