Bridging Theory and Practice: A Review of AI-Driven Techniques for Ground Penetrating Radar Interpretation
Source abstract
Abstract
Artificial intelligence (AI) has emerged as a powerful tool for advancing the interpretation of ground penetrating radar (GPR) data, offering solutions to long-standing challenges in manual analysis, such as subjectivity, inefficiency, and limited scalability. This review investigates recent developments in AI-driven techniques for GPR interpretation, with a focus on machine learning, deep learning, and hybrid approaches that incorporate physical modeling or multimodal data fusion. We systematically analyze the application of these techniques across various domains, including utility detection, infrastructure monitoring, archeology, and environmental studies. Key findings highlight the success of convolutional neural networks in hyperbola detection, the use of segmentation models for stratigraphic analysis, and the integration of AI with robotic and real-time systems. However, challenges remain with generalization, data scarcity, model interpretability, and operational deployment. We identify promising directions, such as domain adaptation, explainable AI, and edge-compatible solutions for practical implementation. By synthesizing current progress and limitations, this review aims to bridge the gap between theoretical advancements in AI and the practical needs of GPR practitioners, guiding future research towards more reliable, transparent, and field-ready systems.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Geophysical Methods and Applications · Landslides and related hazards · Seismic Waves and Analysis
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Faculty of Engineering, Computing and the Environment, Kingston University, London KT1 1LQ, UK
School of Computing and Mathematical Sciences, Birkbeck, University of London, London WC1E 7HX, UK
References (100+)
Show source-provided references
1. Reconstruction of missing ground-penetrating radar traces using simplified U-Net10.1109/LGRS.2021.3072028 ↗
2. Yue, Y., Liu, H., Meng, X., Li, Y., and Du, Y. (2021). Generation of high-precision ground penetrating radar images using improved least square generative adversarial networks. Remote Sens., 13.10.3390/rs13224590 ↗
3. Wang, Q., Chen, Y., Shen, Y., and Li, M. (2024). Construction Environment Noise Suppression of Ground-Penetrating Radar Signals Based on an RG-DMSA Neural Network. Electronics, 13.10.3390/electronics13142843 ↗
4. VAE-ResNet cascade network: An advanced algorithm for stochastic clutter suppression in ground penetrating radar data
5. Enhancing Ground Penetrating Radar (GPR) Data Resolution Through Weakly Supervised Learning
6. Lei, W., Tan, X., Luo, C., and Xue, W. (2024). Mutual Interference Suppression and Signal Enhancement Method for Ground-Penetrating Radar Based on Deep Learning. Electronics, 13.10.3390/electronics13234722 ↗
7. Guiding GPT models for specific one-for-all tasks in ground penetrating radar10.1016/j.autcon.2025.105979 ↗
8. Recognition of void defects in airport runways using ground-penetrating radar and shallow CNN10.1016/j.autcon.2022.104260 ↗
9. Xue, W., Chen, K., Li, T., Liu, L., and Zhang, J. (2023). Efficient underground target detection of urban roads in Ground-Penetrating Radar images based on neural networks. Remote Sens., 15.10.3390/rs15051346 ↗
10. Unsupervised deep learning-based ground penetrating radar image translation for internal defect recognition of underground engineering structures10.1177/14759217231173314 ↗
11. Defect segmentation: Mapping tunnel lining internal defects with ground penetrating radar data using a convolutional neural network10.1016/j.conbuildmat.2021.125658 ↗
12. Integrated ground penetrating radar and deep learning approach for rebar diameter classification in concrete elements10.1007/s11709-025-1177-4 ↗
13. Chen, R., Cao, L., Lu, C., and Liu, L. (2024). Research on Intelligent Recognition Method of Ground Penetrating Radar Images Based on SAHI. Appl. Sci., 14.10.3390/app14188470 ↗
14. Arbitrarily-oriented tunnel lining defects detection from Ground Penetrating Radar images using deep Convolutional Neural networks10.1016/j.autcon.2021.104044 ↗
15. Park, D.W., Kim, H.E., Lee, K., and Park, J. (2024). Development of a Background Filtering Algorithm to Improve the Accuracy of Determining Underground Cavities Using Multi-Channel Ground-Penetrating Radar and Deep Learning. Remote Sens., 16.10.3390/rs16183454 ↗
16. Improving the Performance of Deep-Learning-Based Ground-Penetrating Radar Cavity Detection Model using Data Augmentation and Ensemble Techniques
17. Qiu, Z., Zhao, Z., Chen, S., Zeng, J., Huang, Y., and Xiang, B. (2022). Application of an improved YOLOv5 algorithm in real-time detection of foreign objects by ground penetrating radar. Remote Sens., 14.10.3390/rs14081895 ↗
18. Study on Wavelet Entropy for Airport Pavement Inspection using a Multi-Static GPR System10.1190/geo2020-0361.1 ↗
19. Advances of deep learning applications in ground-penetrating radar: A survey10.1016/j.conbuildmat.2020.120371 ↗
20. Detection of concealed cracks from ground penetrating radar images based on deep learning algorithm10.1016/j.conbuildmat.2020.121949 ↗
21. Detection and localization of rebar in concrete by deep learning using ground penetrating radar10.1016/j.autcon.2020.103279 ↗
22. 3DInvNet: A deep learning-based 3D ground-penetrating radar data inversion
23. Wang, H., Ouyang, S., Liu, Q., Liao, K., and Zhou, L. (2022). Deep-learning-based method for estimating permittivity of ground-penetrating radar targets. Remote Sens., 14.10.3390/rs14174293 ↗
24. Deep learning-based pavement subsurface distress detection via ground penetrating radar data10.1016/j.autcon.2022.104516 ↗
25. Li, Z., Zeng, Z., Xiong, H., Lu, Q., An, B., Yan, J., Li, R., Xia, L., Wang, H., and Liu, K. (2023). Study on rapid inversion of soil water content from ground-penetrating radar data based on deep learning. Remote Sens., 15.10.3390/rs15071906 ↗
26. Ü-Net: Deep-learning schemes for ground penetrating radar data inversion10.2113/JEEG19-074 ↗
27. A machine learning scheme for estimating the diameter of reinforcing bars using ground penetrating radar10.1109/LGRS.2020.2977505 ↗
28. On the use of lateral wave for the interlayer debonding detecting in an asphalt airport pavement using a multistatic GPR system10.1109/TGRS.2019.2961772 ↗
29. A machine learning-based fast-forward solver for ground penetrating radar with application to full-waveform inversion10.1109/TGRS.2019.2891206 ↗
30. GPRTransNet: A deep learning–based ground-penetrating radar translation network10.1016/j.tust.2025.106557 ↗
31. A study of automatic recognition and localization of pipeline for ground penetrating radar based on deep learning
32. Deep neural network-based permittivity inversions for ground penetrating radar data10.1109/JSEN.2021.3050618 ↗
33. Defects identification and location of underground space for ground penetrating radar based on deep learning10.1016/j.tust.2023.105278 ↗
34. Yang, J., Ruan, K., Gao, J., Yang, S., and Zhang, L. (2022). Pavement distress detection using three-dimension ground penetrating radar and deep learning. Appl. Sci., 12.10.3390/app12115738 ↗
35. Bai, X., Yang, Y., Wei, S., Chen, G., Li, H., Li, Y., Tian, H., Zhang, T., and Cui, H. (2023). A comprehensive review of conventional and deep learning approaches for ground-penetrating radar detection of raw data. Appl. Sci., 13.10.3390/app13137992 ↗
36. A GANs-based deep learning framework for automatic subsurface object recognition from ground penetrating radar data10.1109/ACCESS.2021.3064205 ↗
37. Detection of coal fire by deep learning using ground penetrating radar10.1016/j.measurement.2022.111585 ↗
38. Deep learning–based nondestructive evaluation of reinforcement bars using ground-penetrating radar and electromagnetic induction data10.1111/mice.12798 ↗
39. Xu, H., Yan, J., Feng, G., Jia, Z., and Jing, P. (2024). Rock layer classification and identification in ground-penetrating radar via machine learning. Remote Sens., 16.10.3390/rs16081310 ↗
40. GPRInvNet: Deep learning-based ground-penetrating radar data inversion for tunnel linings10.1109/TGRS.2020.3046454 ↗
41. Autonomous pavement distress detection using ground penetrating radar and region-based deep learning10.1016/j.measurement.2020.108077 ↗
42. GPRI2Net: A deep-neural-network-based ground penetrating radar data inversion and object identification framework for consecutive and long survey lines
43. Deep learning for estimating low-range concrete sub-surface boundary depths using ground penetrating radar signals10.1109/LSENS.2022.3147470 ↗
44. Liu, P., Ding, Z., Zhang, W., Ren, Z., and Yang, X. (2023). Using ground-penetrating radar and deep learning to rapidly detect voids and rebar defects in linings. Sustainability, 15.10.3390/su151511855 ↗
45. Nondestructive inspection of tree trunks using a dual-polarized ground-penetrating radar system10.1109/TGRS.2022.3184169 ↗
46. Automatic detection and location of pavement internal distresses from ground penetrating radar images based on deep learning10.1016/j.conbuildmat.2023.134483 ↗
47. Deep learning-based automated underground cavity detection using three-dimensional ground penetrating radar10.1177/1475921719838081 ↗
48. Direct velocity inversion of ground penetrating radar data using GPRNet10.1029/2020JB021047 ↗
49. Deep-learning-guided high-resolution subsurface reflectivity imaging with application to ground-penetrating radar data10.1093/gji/ggac468 ↗
50. Deep learning-based multifrequency ground penetrating radar data merging10.1190/geo2023-0215.1 ↗
51. Permittivity inversion of ground penetrating radar by attention-based deep learning
52. Pavement moisture content prediction: A deep residual neural network approach for analyzing ground penetrating radar
53. Automatic corrosive environment detection of RC bridge decks from ground-penetrating radar data based on deep learning10.1061/(ASCE)CF.1943-5509.0001712 ↗
54. Jin, Y., and Duan, Y. (2020). Wavelet scattering network-based machine learning for ground penetrating radar imaging: Application in pipeline identification. Remote Sens., 12.10.3390/rs12213655 ↗
55. Deep Learning-Based Interpolation for Ground Penetrating Radar Data Reconstruction10.1109/JSTARS.2025.3543256 ↗
56. Intelligent recognition of ground penetrating radar images in urban road detection: A deep learning approach10.1007/s13349-024-00818-5 ↗
57. Two-stage Denoising of Ground Penetrating Radar Data based on Deep Learning10.1109/LGRS.2024.3489635 ↗
58. Three-dimensional convolutional neural network–based underground object classification using three-dimensional ground penetrating radar data10.1177/1475921720902700 ↗
59. Semisupervised deep neural network-based cross-frequency ground-penetrating radar data inversion10.1109/TGRS.2023.3334492 ↗
60. Simultaneous tunnel defects and lining thickness identification based on multi-tasks deep neural network from ground penetrating radar images10.1016/j.autcon.2022.104633 ↗
61. Trunk health condition inspection using integrated 3D photogrammetry and holographic radar tomography10.1109/TGRS.2025.3577556 ↗
62. Zou, L., Wang, Y., Giannakis, I., Tosti, F., Alani, A.M., and Sato, M. (2020). Mapping and Assessment of Tree Roots Using Ground Penetrating Radar with Low-Cost GPS. Remote Sens., 12.10.3390/rs12081300 ↗
63. Underground target localization method for ground penetrating radar based on deep learning10.1016/j.measurement.2025.117647 ↗
64. Torbali, M.E., Zolotas, A., and Avdelidis, N.P. (2023). A state-of-the-art review of non-destructive testing image fusion and critical insights on the inspection of aerospace composites towards sustainable maintenance repair operations. Appl. Sci., 13.10.3390/app13042732 ↗
65. Machine learning for data-driven discovery in solid Earth geoscience10.1126/science.aau0323 ↗
66. Enhancing Deep Learning-Based GPR Data Inversion with Unsupervised Domain Adaptation: Comparison of Domain Classifiers10.1109/TGRS.2025.3568384 ↗
67. Lightweight deep learning model for identifying tunnel lining defects based on GPR data10.1016/j.autcon.2024.105506 ↗
68. FM-GAN: Forward modeling network for generating approaching-reality B-scans of GPR pipelines with transformer tuning
69. Deep Learning Inversion of Ground Penetrating Radar with Prior Physical Velocity Field for Complex Subsurface Root System
70. A Deep Learning-Based Method for Attenuation Compensation in Ground-Penetrating Radar
71. Application of convolutional and recurrent neural networks for buried threat detection using ground penetrating radar data10.1109/TGRS.2020.2978763 ↗
72. Li, X., Cheng, X., Zhao, Y., Xiang, B., and Zhang, T. (2025). Deep Learning-Based Ground-Penetrating Radar Inversion for Tree Roots in Heterogeneous Soil. Sensors, 25.10.3390/s25030947 ↗
73. Pavement-distress detection using ground-penetrating radar and network in networks10.1016/j.conbuildmat.2019.117352 ↗
74. Advances in automatic identification of road subsurface distress using ground penetrating radar: State of the art and future trends10.1016/j.autcon.2023.105185 ↗
75. Multi-depth soil moisture estimation via 1D convolutional neural networks from drone-mounted ground penetrating Radar data10.1016/j.compag.2025.110104 ↗
76. Surface Permittivity Estimation of Southern Utopia Planitia by High-Frequency RoPeR in Tianwen-1 Mars Exploration
77. GPR-GAN: A ground-penetrating radar data generative adversarial network
78. A deep learning-based GPR forward solver for predicting B-scans of subsurface objects
79. Feng, D., Liu, Y., Zhang, B., and Wang, X. (2023). Special Issue on Ground Penetrating Radar: Theory, Methods, and Applications. Appl. Sci., 13.10.3390/app13179847 ↗
80. Crevasse detection in ice sheets using ground penetrating radar and machine learning10.1109/JSTARS.2014.2332872 ↗
81. Enhanced ground-penetrating radar inversion with closed-loop convolutional neural networks
82. A Semisupervised Deep Learning Method for Ground Penetrating Radar Data Inversion and Concrete Subsurface Defect Imaging
83. Bi, B., Shen, L., Zhang, P., Huang, X., Xin, Q., and Jin, T. (2023). TSVR-net: An end-to-end ground-penetrating radar images registration and location network. Remote Sens., 15.10.3390/rs15133428 ↗
84. Lin, Y., Wang, J., Ma, D., Wang, Y., and Ye, S. (2024). Improved Cycle-Consistency Generative Adversarial Network-Based Clutter Suppression Methods for Ground-Penetrating Radar Pipeline Data. Remote Sens., 16.10.3390/rs16061043 ↗
85. Enhancing Interpretability in Deep Learning-Based Inversion of 2D Ground Penetrating Radar Data: An Explainable AI (XAI) Strategy
86. Automatic classification of pavement distress using 3D ground-penetrating radar and deep convolutional neural network10.1109/TITS.2022.3197712 ↗
87. A novel convolutional autoencoder-based clutter removal method for buried threat detection in ground-penetrating radar10.1109/TGRS.2021.3098122 ↗
88. Automated assessment of reinforced concrete elements using ground penetrating radar10.1016/j.autcon.2022.104378 ↗
89. Zheng, X., Fang, S., Chen, H., Peng, L., and Ye, Z. (2023). Internal detection of ground-penetrating radar images using YOLOX-s with modified backbone. Electronics., 12.10.3390/electronics12163520 ↗
90. End-to-end deep learning model for underground utilities localization using GPR10.1016/j.autcon.2023.104776 ↗
91. Iterative application of generative adversarial networks for improved buried pipe detection from images obtained by ground-penetrating radar10.1111/mice.13070 ↗
92. CIGGAN: A Ground Penetrating Radar Image Generation Method based on Feature Fusion
93. Classification of Buried Objects from Ground Penetrating Radar Images by using Second Order Deep Learning Models10.1109/JSTARS.2024.3524424 ↗
94. Kumar, A., Singh, U.K., and Pradhan, B. (2022). Ground penetrating radar in coastal hazard mitigation studies using deep convolutional neural networks. Remote Sens., 14.10.3390/rs14194899 ↗
95. Automated rebar recognition and corrosion assessment of concrete bridge decks using ground penetrating radar10.1016/j.autcon.2024.105631 ↗
96. Ice thickness from deep learning and conditional random fields: Application to ice-penetrating radar data with radiometric validation
97. YOLOv11-CAFM model in ground penetrating radar image for pavement distress detection and optimization study10.1016/j.conbuildmat.2025.141907 ↗
98. Wang, S., Gong, X., and Han, L. (2024). Monte Carlo full-waveform inversion of cross-hole ground-penetrating radar data based on improved residual network. Remote Sens., 16.10.3390/rs16020243 ↗
99. MPPINet: Multi-Path Permittivity Inversion Network for Tree Roots Ground Penetrating Radar Image Recognition
100. Siam-Gabor-ResNet Used for Crevasse Detection with Ground Penetrating Radar Data