Physics-Aware Machine Learning for Dynamic, Data-Driven Radar Target Recognition

Despite advances in Artificial Intelligence and Machine Learning (AI/ML) for automatic target recognition (ATR) using surveillance radar, there remain significant challenges to robust and accurate perception in operational environments. Physics-aware ML is an emerging field that strives to integrate physics-based models with data-driven deep learning (DL) to reap the benefits of both approaches. Physics-based models allow for the prediction of the expected radar return given any sensor position, observation angle and environmental scene. However, no model is perfect and the dynamic nature of the sensing environment ensures that there will always be some part of the signal that is unknown, which can be modeled as noise, bias or error uncertainty. Physics-aware machine learning combines the strengths of DL and physics-based modeling to optimize trade-offs between prior versus new knowledge, models vs. data, uncertainty, complexity, and computation time, for greater accuracy and robustness. This paper addresses the challenge of designing physics-aware synthetic data generation techniques for training deep models for ATR. In particular, physics-based methods for data synthesis, the limitations of current generative adversarial network (GAN)-based methods, new ways domain knowledge may be integrated for new GAN architectures and domain adaptation of signatures from different, but related sources of RF data, are presented. The use of a physics-aware loss term with a multi-branch GAN (MBGAN) resulted in a 9% improvement in classification accuracy over that attained with the use of real data alone, and a 6% improvement over that given using data generated by a Wasserstein GAN with gradient penalty. The implications for DL-based ATR in Dynamic Data-Driven Application Systems (DDDAS) due to fully-adaptive transmissions are discussed.