Efficient Deep-Learning-Driven Sparse-Target Imaging Method for Array Borehole Radar in Nonuniform Medium

In this study, an efficient deep-learning-driven sparse-target imaging (DLSTI) method was developed for array borehole radar to improve the accuracy of target localization in a subsurface nonuniform media. First, by making use of the linear superposition and separable characteristics of the target and background echo, the background echo was generated with an electromagnetic (EM) simulation using prior medium information. The background echo was then removed from the radar receiver echo using a convex-optimization-based front-end target echo extractor (TEE) to obtain the raw sparse target echo. Subsequently, the raw target echoes and true target locations in the simulation dataset were utilized for the training of a back-end stacked autoencoder (SAE) in a data-driven manner, which is capable of illustrating accurate target locations in field tests in nonuniform environments after training. The comparison results in multiple simulations and field scenes show that the proposed DLSTI outperforms other effective imaging methods in terms of target localization accuracy and image sidelobes (SLs), including reverse time migration and back-projection (BP), whose localization error was improved to 0.02 m and the image SL was reduced by 16.09 dB.