Deep Learning for Improved Subsurface Imaging: Enhancing GPR Clutter Removal Performance Using Contextual Feature Fusion and Enhanced Spatial Attention

In engineering practice, ground penetrating radar (GPR) records are often hindered by clutter resulting from uneven underground media distribution, affecting target signal characteristics and precise positioning. To address this issue, we propose a method combining deep learning preprocessing reverse time migration (RTM) imaging. Our approach introduces novel framework for GPR clutter, enhancing the network’s feature-capture capability signals through integration of contextual feature fusion module (CFFM) an enhanced spatial attention (ESAM). The superiority effectiveness our algorithm demonstrated RTM imaging comparisons using synthetic laboratory data. processing actual road data further confirms algorithm’s significant potential practical applications.