1887

Abstract

Summary

Machine learning applications are gaining popularity in geophysical applications, as they are able to circumvent inverse problems through statistical relationships. Among others, Bayesian Evidential Learning (BEL) enables dynamic data integration and allows for uncertainty quantification. It relies on a simulation-based prior that through statistical relationships identifies the correlation between a given frame and an observed dataset in a computational non-demanding way.

In the work here presented, we apply BEL on the surface wave analysis problem, that is usually marked by subjective decision-making for dispersion curve and mode picking and depends on deterministic or stochastic inversion schemes. Interface seismic waves, such as Rayleigh, Love and Scholte waves, exhibit frequency-dependent phase velocities, i.e., dispersion, that can be used to image the near-surface. We use wavefield transform methods to identify surface wave dispersion from observed seismic shot gathers, that given a prior model space, can be directly used on the transform i.e., without dispersion curve extraction, to predict an ensemble of 1D near-surface profiles mapping selected parameters such as velocity, density or attenuation. Simultaneously, we are able to quantify the uncertainty of the solution ensemble as well as to detect if the considered wavefield transform falls outside of the defined prior.

© EAGE Publications BV
Loading

Article metrics loading...

/content/papers/10.3997/2214-4609.202520096
2025-09-07
2026-02-13

  • From This Site

    /content/papers/10.3997/2214-4609.202520096
    dcterms_title,dcterms_subject,pub_keyword
    -contentType:Journal -contentType:Contributor -contentType:Concept -contentType:Institution
    10
    5
Loading full text...

Full text loading...

References

  1. Ahmed, A., Aigner, L., Michel, H., Deleersnyder, W., Dudal, D., Flores Orozco, A. and Hermans, T. [2024] Assessing and Improving the Robustness of Bayesian Evidential Learning in One Dimension for Inverting Time-Domain Electromagnetic Data: Introducing a New Threshold Procedure. Water, 16(7), 1056.
     [Google Scholar]
  2. Dal Moro, G., Coviello, V. and Carlo, G.D. [2015] Shear-Wave Velocity Reconstruction via Unconventional Joint Analysis of Surface Waves: A Case Study in the Light of Some Theoretical Aspects. In: Engineering Geology for Society and Territory-Volume 5: Urban Geology, Sustainable Planning and Landscape Exploitation. Springer, 1177–1182.
     [Google Scholar]
  3. Dou, S. and Ajo-Franklin, J.B. [2014] Full-wavefield inversion of surface waves for mapping embedded low-velocity zones in permafrost. Geophysics, 79(6), EN107–EN124.
     [Google Scholar]
  4. Forbriger, T. [2003a] Inversion of shallow-seismic wavefields: I. Wavefield transformation. Geophysical Journal International, 153(3), 719–734.
     [Google Scholar]
  5. Forbriger, T. [2003b] Inversion of shallow-seismic wavefields: II. Inferring subsurface properties from wavefield transforms. Geophysical Journal International, 153(3), 735–752.
     [Google Scholar]
  6. Hermans, T., Lesparre, N., De Schepper, G. and Robert, T. [2019] Bayesian evidential learning: a field validation using push-pull tests. Hydrogeology Journal, 27(5), 1661–1672.
     [Google Scholar]
  7. Liu, H., Li, J. and Hu, R. [2024] Automatic and adaptive picking of surface-wave dispersion curves for near-surface application. Journal of Applied Geophysics, 221, 105282.
     [Google Scholar]
  8. Michel, H., Hermans, T. and Nguyen, F. [2023] Iterative prior resampling and rejection sampling to improve 1-D geophysical imaging based on Bayesian evidential learning (BEL1D). Geophysical Journal International, 232(2), 958–974.
     [Google Scholar]
  9. Michel, H., Nguyen, F. and Aigner, L. [2022] hadrienmichel/pyBEL1D: Latest version of pyBEL1D. Accessed: 2022-08-04.
     [Google Scholar]
  10. Niskanen, M. and Lähivaara, T. [2023] COMPOSTI: A Python-based program for seismic trans-dimensional inversion. SoftwareX, 21, 101298.
     [Google Scholar]
  11. Niu, Y., Elita Li, Y. and Chen Chian, S. [2022] Full phase-velocity spectrum inversion of multimode Rayleigh waves. In: Second International Meeting for Applied Geoscience & Energy. Society of Exploration Geophysicists and American Association of Petroleum…, 2066–2070.
     [Google Scholar]
  12. Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., Blondel, M., Prettenhofer, P., Weiss, R., Dubourg, V. et al. [2011] Scikit-learn: Machine learning in Python. the Journal of machine Learning research, 12, 2825–2830.
     [Google Scholar]
  13. Ryden, N. and Park, C.B. [2006] Fast simulated annealing inversion of surface waves on pavement using phase-velocity spectra. Geophysics, 71(4), R49–R58.
     [Google Scholar]
  14. Scheidt, C., Li, L. and Caers, J. [2018] Quantifying uncertainty in subsurface systems, 236. John Wiley & Sons.
     [Google Scholar]
  15. Tokimatsu, K., Tamura, S. and Kojima, H. [1992] Effects of multiple modes on Rayleigh wave dispersion characteristics. Journal of geotechnical engineering, 118(10), 15290–1543.
     [Google Scholar]
  16. Vantassel, J.P. and Cox, B.R. [2022] SWprocess: a workflow for developing robust estimates of surface wave dispersion uncertainty. Journal of Seismology, 26(4), 731–756.
     [Google Scholar]
  17. Wang, Z., Sun, C. and Wu, D. [2021] Automatic picking of multi-mode surface-wave dispersion curves based on machine learning clustering methods. Computers & Geosciences, 153, 104809.
     [Google Scholar]
  18. Zhang, X., Zheng, Y. and Curtis, A. [2023] Surface wave dispersion inversion using an energy likelihood function. Geophysical Journal International, 232(1), 523–536.
     [Google Scholar]
  19. Zhang, Z., Alkhalifah, T. and Liu, Y. [2024] Full Dispersion-Spectrum Inversion of Surface Waves. Journal of Geophysical Research: Solid Earth, 129(6), e2023JB028469.
     [Google Scholar]
/content/papers/10.3997/2214-4609.202520096
Loading
1D Surface Wave Modeling with Bayesian Evidential Learning
Conference Proceedings 2025, 1 (2025); https://doi.org/10.3997/2214-4609.202520096
/content/papers/10.3997/2214-4609.202520096
/content/papers/10.3997/2214-4609.202520096
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