GPR-TransUNet: An improved TransUNet based on self-attention mechanism for ground penetrating radar inversion

• Published in: Journal of applied geophysics Vol. 222; p. 105333
• Main Authors: Junkai, Ge, Huaifeng, Sun, Wei, Shao, Dong, Liu, Yuhong, Yao, Yi, Zhang, Rui, Liu, Shangbin, Liu
• Format: Journal Article
• Language: English
• Published: Elsevier B.V 01.03.2024
• Subjects: Deep learning; GPR; Inversion; Deep learning; GPR; Inversion
• ISSN: 0926-9851; 1879-1859
• DOI: 10.1016/j.jappgeo.2024.105333

Convolutional Neural Networks (CNN) are widely applied to Ground Penetrating Radar (GPR) inversion because they have strong data-driven capabilities and are suitable for the data structure form of GPR. For CNN, the computation increases with the distance that the convolutional block moves from one region to another when it calculates the relationship between two regions. For GPR data, the target reflection exists in the surrounding traces and full time-window of the target, which leads to high degree of remote relationship. In this paper, we propose GPR-TransUNet, a deep-learning based inversion network which use self-attention mechanism. According to the characteristics of GPR data, regression network and GPR-Loss mechanism were used. Both numerical and model experiments were arranged to test the performance of the network, and the result as well as comparative analysis demonstrate the superiority of GPR-TransUNet. Finally, we applied this method to the field GPR data of Guangxi as an attempt. [Display omitted] •GPR-TransUNet based on Regressive Self-Attention Mechanism and U-net is proposed.•GPR-TransUNet is successfully used to reconstruct the permittivity map of complex subsurface defects.•GPR-TransUNet is verified by synthetic and field data.