A Deep-Learning-Based Method for Attenuation Compensation in Ground-Penetrating Radar

Ground-penetrating radar (GPR) is an essential tool for nondestructive subsurface exploration. However, electromagnetic wave propagation in underground environments is severely attenuated, leading to the loss of important geological information and limiting the resolution of underground imaging. To address this challenge, we propose an attention-enhanced U-Net (AEU-Net) model for GPR signal attenuation compensation. This model builds upon the 1-D U-Net architecture and integrates a feature fusion attention block (FFAB) to effectively capture both local and global features, thereby enhancing its capability to process complex datasets. In addition, to overcome dataset acquisition challenges, we use GprMax software to simulate realistic geological structures based on the relationship between conductivity and electromagnetic wave attenuation, thereby generating the training dataset. Experimental results with synthetic and field data demonstrate that the proposed method significantly improves noise robustness, restores fine subsurface details, and effectively compensates for GPR signal attenuation, thereby showing its potential for high-resolution underground imaging.