1887

Abstract

Summary

Cross-hole ground penetrating radar (GPR) full waveform inversion (FWI) is a powerful technique for high-resolution imaging of subsurface properties. However, the traditional FWI method presents challenges such as falling into local minima and high computational costs. Data-driven deep learning is considered a potential solution to the FWI problem, while its ability is limited in the cross-hole GPR FWI due to the lack of sufficient labeled samples. To alleviate these difficulties, we propose ADMM-Unet, a deep iterative unfolding network that integrates physics-driven principles into deep learning, for cross-hole GPR FWI. ADMM-Unet does not rely on source wavelet estimation by using a convolutional objective function, and it decomposes the inversion problem into three subproblems based on the Alternating Direction Method of Multipliers (ADMM) algorithm. The gradient used to update the permittivity model is calculated by automatic differentiation, and a soft-threshold-based convolutional neural network is designed to learn the proximal operator in the regularization subproblem. Experimental results show that the proposed method significantly improves inversion accuracy and computational efficiency compared to traditional FWI methods with L1 or L2 regularization.

© EAGE Publications BV
Loading

Article metrics loading...

/content/papers/10.3997/2214-4609.202572075
2025-05-13
2026-02-16

  • From This Site

    /content/papers/10.3997/2214-4609.202572075
    dcterms_title,dcterms_subject,pub_keyword
    -contentType:Journal -contentType:Contributor -contentType:Concept -contentType:Institution
    10
    5
Loading full text...

Full text loading...

References

  1. Choi, Y., Shin, C., Min, D. J. and Ha, T. [2005]. Efficient calculation of the steepest descent direction for source-independent seismic waveform inversion: An amplitude approach. Journal of Computational Physics, 208(2), 455–468.
     [Google Scholar]
  2. Liu, B., Ren, Y., Liu, H., Xu, H., Wang, Z., Cohn, A. G. and Jiang, P. [2021]. GPRInvNet: Deep learning-based ground-penetrating radar data inversion for tunnel linings. IEEE Transactions on Geoscience and Remote Sensing, 59(10), 8305–8325.
     [Google Scholar]
  3. Liu, H., Wang, J., Zhang, J., Jiang, H., Xu, J., Jiang, P., Zhang, F., Sui, Q. and Wang, Z. [2023]. Semi-supervised deep neural network-based cross-frequency ground-penetrating radar data inversion. IEEE Transactions on Geoscience and Remote Sensing, 61, 5109519.
     [Google Scholar]
  4. Liu, Y., Feng, D., Xiao, Y., Huang, G., Cai, L., Tai, X. and Wang, X. [2024]. Full Waveform Inversion of Multi-frequency GPR data using a Multiscale Approach based on Deep Learning. IEEE Transactions on Geoscience and Remote Sensing, 62, 5910212.
     [Google Scholar]
  5. Sun, H., Yang, X., Gong, J., Qu, X. and Lan, T. [2022]. Joint physics and data driven full-waveform inversion for underground dielectric targets imaging. IEEE Transactions on Geoscience and Remote Sensing, 60, 4513311.
     [Google Scholar]
  6. Zhang, J. and Ghanem, B. [2018]. ISTA-Net: Interpretable optimization-inspired deep network for image compressive sensing. 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).
     [Google Scholar]
/content/papers/10.3997/2214-4609.202572075
Loading
Crosshole GPR Full Waveform Inversion with a Deep Iterative Unfolding Network
Conference Proceedings 2025, 1 (2025); https://doi.org/10.3997/2214-4609.202572075
/content/papers/10.3997/2214-4609.202572075
/content/papers/10.3997/2214-4609.202572075
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