Autonomous Assessment of Airspace Operations

NASA’s 2018 SBIR solicitation topic A3.02 requests “Autonomous systems to produce any of the following system capabilities: Prognostics, data mining, and data discovery to identify opportunities for improvement in airspace operations.” Identifying opportunities for improvement is a critical ongoing need in the air traffic management domain, for which achieving high levels of performance is a daily concern. Its importance will continue as traffic volumes grow and new vehicle classes are introduced. In particular, as new Urban Air Mobility (UAM) operations become more prevalent, methodologies to quantify performance of both human-centered and autonomous operations will be required. The objective of this work is to discover opportunities for improvement in operations of the National Airspace System (NAS), using methods that advance the state of the art and that can be applied to both current and future operations. To that end, Mosaic ATM proposes to develop a tool that will characterize and classify the efficiency of airspace operations, with a focus on airport metroplex operations. We propose to leverage the latest in machine learning techniques to create supervised and unsupervised machine learning models, which will be trained and validated using large sets of archived flight and weather data. These models will be able to identify the most critical causal factors for degraded performance conditions, in a way that is comprehensible to an analyst. We will provide a user interface to explore the model results and causal factors. This work will support planning for UAM operations as well as informing NASA and other stakeholders where further investments in NAS automation are most warranted.