Applying Generative Adversarial Networks to Intelligent Subsurface Imaging and Identification
This work addresses data scarcity in subsurface imaging for applications like GPR analysis, representing an incremental improvement with a domain-specific focus.
This thesis tackled the problem of limited training data for Ground Penetrating Radar (GPR) classification by generating realistic GPR B-scans using a novel Generative Adversarial Network architecture, resulting in an increase in object classifier accuracy from 82% to 98%.
To augment training data for machine learning models in Ground Penetrating Radar (GPR) data classification and identification, this thesis focuses on the generation of realistic GPR data using Generative Adversarial Networks. An innovative GAN architecture is proposed for generating GPR B-scans, which is, to the author's knowledge, the first successful application of GAN to GPR B-scans. As one of the major contributions, a novel loss function is formulated by merging frequency domain with time domain features. To test the efficacy of generated B-scans, a real time object classifier is proposed to measure the performance gain derived from augmented B-Scan images. The numerical experiment illustrated that, based on the augmented training data, the proposed GAN architecture demonstrated a significant increase (from 82% to 98%) in the accuracy of the object classifier.