Abstract
To address the limitations of traditional empirical interpretation methods for advanced ground penetrating radar (GPR) detection images of tunnels, including inconsistent standards, low efficiency, and high rates of misinterpretation and missed detection, this study proposed an intelligent inversion method for radar B-scan waveform images of adverse geology based on an improved generative adversarial network (GAN). A multi-condition synthetic dataset was constructed through electromagnetic numerical simulation combined with random generation constraints of medium parameters, incorporating three types of geological anomalies (irregular cavities, fracture zones, and cracks) and their combinations. The GAN generator was optimized by integrating Unet convolutional neural network architecture and dilated convolution modules, and structural similarity (SSIM) loss function was incorporated into the loss function to enhance the extraction capability of waveform image features and model inversion performance. Training evaluation results demonstrate that the improved GAN model achieves approximately 4% and 10% higher inversion accuracy than conventional GAN and standalone Unet models, respectively. An inversion experiment using actual engineering data from fracture zone prediction was carried out. Comparative analysis with digital drilling and excavation verification data confirms that the inversion prediction results of the proposed method are basically consistent with actual conditions, and it can provide reliable geological forecasting for tunnel excavation and support.
Publication Date
8-16-2026
DOI
10.14048/j.issn.1671-2579.2026.04.026
First Page
243
Last Page
251
Submission Date
August 2026
Recommended Citation
Wenbin, Tang; Ming, Liang; and Hao, Peng
(2026)
"Intelligent inversion of advanced GPR images for complex adverse geological tunnels,"
Journal of China & Foreign Highway: Vol. 46:
Iss.
4, Article 26.
DOI: 10.14048/j.issn.1671-2579.2026.04.026
Available at:
https://zwgl1980.csust.edu.cn/journal/vol46/iss4/26
Reference
[1]李术才,刘斌,孙怀凤,等.隧道施工超前地质预报研究现状及发展趋势 [J].岩石力学与工程学报,2014,33(6):1090 -1113.Li Shucai,Liu Bin,Sun Huaifeng,et al.State of art and trends of advanced geological prediction in tunnel construction [J].Chinese Journal of Rock Mechanics and Engineering,2014,33(6):1090 -1113.
[2]《中国公路学报 》编辑部.中国交通隧道工程学术研究综述·2022 [J].中国公路学报,2022,35(4):1-40.Editorial Department of China Journal of Highway and Transport.Review on China ’s traffic tunnel engineering research:2022 [J].China Journal of Highway and Transport,2022,35(4):1-40.
[3]张坤牧,彭浩,梁铭,等.基于随钻测量技术的隧道岩体完整性定量评价 [J].中外公路,2025,45(6):245-253.Zhang Kunmu,Peng Hao,Liang Ming,et al.Quantitative evaluation of tunnel rock mass integrity based on MWD technology [J].Journal of China & Foreign Highway,2025,45(6):245-253.
[4]郑健龙,陈梦洁,刘超超.公路基础设施智能建造发展与展望综述 [J].中外公路,2025,45(2):1-20.Zheng Jianlong,Chen Mengjie,Liu Chaochao.Review of intelligent construction development of highway infrastructures and its prospects [J].Journal of China & Foreign Highway,2025,45(2):1-20.
[5]王敏玲,梁值欢,王洪华,等.探地雷达逆时偏移成像方法研究现状及进展 [J].地球物理学进展,2019,34(5):2087 -2096.Wang Minling,Liang Zhihuan,Wang Honghua,et al.Review of reverse time migration in ground penetrating radar [J].Progress in Geophysics,2019,34(5):2087 -2096.
[6]张崇民,张凤凯,李尧.隧道施工不良地质探地雷达超前探测全波形反演研究 [J].隧道建设 (中英文 ),2019,39(1):102-109.Zhang Chongmin,Zhang Fengkai,Li Yao.Study of full waveform inversion of advance tunnel geological prediction by ground penetrating radar [J].Tunnel Construction,2019,39(1):102-109.
[7]Solla M,Pérez-gracia V,Fontul S.A review of GPR application on transport infrastructures:Troubleshooting and best practices [J].Remote Sensing,2021,13(4):672.
[8]Alvarez J K,Kodagoda S.Application of deep learning image-to-image transformation networks to GPR radargrams for sub-surface imaging in infrastructure monitoring [C]//2018 13th IEEE Conference on Industrial Electronics and Applications (ICIEA ).Wuhan,China.IEEE,2018:611-616.
[9]Xie L H,Zhao Q,Ma C G,et al.U-net:Deep-learning schemes for ground penetrating radar data inversion [J].Journal of Environmental and Engineering Geophysics,2020,25(2):287-292.
[10]Liu B,Ren Y X,Liu H C,et al.GPRInvNet:Deep learning-based ground-penetrating radar data inversion for tunnel linings [J].IEEE Transactions on Geoscience and Remote Sensing,2021,59(10):8305 -8325.
[11]Wang J,Liu H C,Jiang P,et al.GPRI 2Net:A deep-neural-network-based ground penetrating radar data inversion and object identification framework for consecutive and long survey lines [J].IEEE Transactions on Geoscience and Remote Sensing,2022,60:5106320.
[12]Ji Y T,Zhang F K,Wang J,et al.Deep neural network-based permittivity inversions for ground penetrating radar data[J].IEEE Sensors Journal,2021,21(6):8172 -8183.
[13]邓宇,肖建平,刘郅静,等.基于改进 UNet的探地雷达信号反演 [J].现代雷达,2023,45(12):31-39.Deng Yu,Xiao Jianping,Liu Zhijing,et al.Signal inversion of ground penetrating radar based on improved UNet [J].Modern Radar,2023,45(12):31-39.
[14]武铭泽,刘庆华,欧阳缮.基于生成对抗网络的两阶段探地雷达图像反演方法 [J].电波科学学报,2025,40(1):141-154.Wu Mingze,Liu Qinghua,Ouyang Shan.Two-stage GPR image inversion method based on generative adversarial network [J].Chinese Journal of Radio Science,2025,40(1):141-154.
[15]刘东坤,巨能攀,霍宇翔.地质雷达在不同介质填充下的频谱差异分析 [J].现代隧道技术,2013,50(5):23-28.Liu Dongkun,Ju Nengpan,Huo Yuxiang.Analysis of the spectrum difference of ground penetrating radar (GPR ) for different media fillings [J].Modern Tunnelling Technology,2013,50(5):23-28.
[16]孙怀凤,程铭,吴启龙,等.瞬变电磁三维 FDTD正演多分辨网格方法 [J].地球物理学报,2018,61(12):5096 -5104.Sun Huaifeng,Cheng Ming,Wu Qilong,et al.A multi-scale grid scheme in three-dimensional transient electromagnetic modeling using FDTD [J].Chinese Journal of Geophysics,2018,61(12):5096 -5104.
[17]Goodfellow I J,Pouget-Abadie J,Mirza M,et al.Generative adversarial nets [C].Proceedings of the 27th International Conference on Neural Information Processing Systems,Montreal,Canada,2014.
[18]Wang Y Z,Qin H,Miao F.A multi-path encoder network for GPR data inversion to improve defect detection in reinforced concrete [J].Remote Sensing,2022,14(22):5871.
[19]李世念,王秀荣,林恬,等.基于 GprMax 的道路空洞三维探地雷达正演数值模拟 [J].中国地质灾害与防治学报,2020,31(3):132-138.Li Shinian,Wang Xiurong,Lin Tian,et al.Numerical simulation of 3D ground penetrating radar based on GprMax for the road cavity [J].The Chinese Journal of Geological Hazard and Control,2020,31(3):132-138.
[20]李荣鹏,宋学力,易稳,等.基于混合高斯分布的联合鲁棒稀疏贝叶斯学习结构损伤识别模型 [J].中国公路学报,2024 (5):300-313.Li Rongpeng,Song Xueli,Yi Wen,et al.A joint robust sparse Bayesian learning model with the mixture of Gaussians for the structural damage identificatio [J].China Journal of Highway and Transport,2024 (5):300-313.
[21]田岗,张海军,王成亮,等.城市道路地下病害识别及塌陷风险评价研究 [J].中外公路,2025,45(2):46-54.Tian Gang,Zhang Haijun,Wang Chengliang,et al.Research on identification of subsurface defects of urban roads and collapse risk assessment [J].Journal of China & Foreign Highway,2025,45(2):46-54.
[22]Gao R.Rethinking dilated convolution for real-time semantic segmentation [C]//2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW ).Vancouver,BC,Canada.IEEE,2023:4675 -4684.
[23]张志宇,李新利,杨国田.基于改进生成对抗网络pix2pix的火电厂 NO x排放预测 [J].中国电机工程学报,2023,43(12):4678 -4687.Zhang Zhiyu,Li Xinli,Yang Guotian.NO x emission prediction of thermal power plant based on improved generative adv ersarial network pix 2pix[J].Proceedings of the CSEE,2023,43(12):4678 -4687.