Explainable Artificial Intelligence (XAI) for Air Traffic Management

Machine Learning (ML) and Artificial Intelligence (AI) have matured to the point where they are being used throughout many modern applications. nbsp;Explainable AI (XAI) ndash; AI in which humans can understand the decisions or predictions made by the AI system ndash; is becoming critical for many applications, including Air Traffic Management (ATM). In contrast, ML-enabled and AI-enabled systems too often resemble ldquo;black boxesrdquo; that mysteriously convert incoming data into predicted outcomes. nbsp;At best, such ldquo;black boxrdquo; systems can be explained by inferred explanations where the input/output relationships are analyzed and generalized.nbsp; Even the designers of such systems cannot explain why the AI or ML system arrived at a specific decision.nbsp;nbsp;Outcomes of such ldquo;intelligent systemsrdquo; should resonate with the decision makersrsquo; own expertise, understanding, and intuitions (tacit knowledge). nbsp; This effort sspecifically merges deep generative models, optimal transport theory along with AI Intent Inference Learning (IIL) to create a vocabulary for XAI that can be used to explain ATM-domain situations.