FM-GAN: Forward Modeling Network for Generating Approaching-Reality B-Scans of GPR Pipelines With Transformer Tuning

Ground-penetrating radar (GPR) forward modeling holds significant importance in the realms of geological exploration, subsurface target detection, and scientific research. With the growing use of deep learning in GPR data processing, the need for extensive datasets that closely resemble real-world scenarios has become essential. However, acquiring such approaching-reality datasets is challenging. This article introduces forward modeling generative adversarial network (FM-GAN), a network designed to generate B-scan images of underground pipelines across different mediums. Our adaptive spatial polarization generator, part of this network, processes dielectric constant images to create B-scan images that closely mimic real environmental data. It includes spatially adaptive normalization modules, adaptformer modules, and a double SimAM feature fusion attention module (DSFFA) for feature fusion and B-scan image generation. We train the network using paired data from underground dielectric constant models and B-scan data simulated through finite-difference time-domain (FDTD) techniques. Specifically, we apply transformer fine-tuning methods to enhance its adaptability to real-world environments. This research combines deep learning, conditional generative adversarial networks (CGANs), and the vision transformer (ViT) to model underground pipeline dielectric constants. Empirical results show that our approach performs similar to the FDTD method on both single and mixed dielectric constant data, significantly improving computational efficiency. This methodology holds promise for advancing underground structure imaging and interpretation, paving the way for innovative applications in underground surveys and GPR technology.