StratGAN: Conditional Adversarial Network for Permittivity Inversion of Borehole Radar Data in Stratified Media

An ill-posed permittivity inversion problem is encountered in borehole radar (BHR) applications within stratified media due to a highly nonlinear forward relation, insufficient statistical coverage under data-limited conditions, strong noise contamination, and limited borehole observation geometry, which together cause instability and blurred boundaries. To address these challenges, a stratified media oriented conditional generative adversarial network for permittivity inversion, termed StratGAN, is proposed. BHR waveform data are used as the conditional input, and the complex mapping from time domain waveforms to depth domain permittivity distributions is learned end to end through conditional adversarial training between a generator and a discriminator, jointly constrained by a composite loss. During training, statistical characteristics of layered structures are learned from real samples by the discriminator, and adaptive feedback is provided as a data-driven loss to suppress spurious structures and boundary ambiguity. WGAN-GP is adopted and combined with a patch-based local discrimination mechanism to reinforce high-frequency details and geometric boundary consistency, thereby reducing the over-smoothing tendency of conventional CNNs. In addition, geometric consistency of inversion results is improved in an end-to-end manner without relying on complicated velocity analysis. Quantitative evaluations on simulated and measured datasets indicate that, compared with an architecture-matched convolutional neural network (CNN) and the baseline model GPRNet, StratGAN achieves overall better performance in terms of mean absolute error, coefficient of determination, and structural similarity metrics, and layered interfaces and anomaly boundaries are more effectively recovered. For the controlled measured data, the coefficient of determination (R2) is improved to 0.9533 by StratGAN, whereas a value of 0.5598 is obtained by GPRNet. These results indicate the potential of StratGAN to enhance the reliability and structural fidelity of BHR permittivity inversion under limited-sample conditions, and preliminary evidence is provided for its practical applicability under controlled measured conditions.