CAREER: Proactive and Practical Management of Air Traffic Disruptions

Air transportation is a critical component of national infrastructure, enabling economic activity, connecting communities across the United States, and supporting global travel and trade. Millions of passengers depend on this system each day, yet it remains vulnerable to disruptions caused by severe weather, staffing shortages, equipment failures, and other unexpected events. As these disruptions become more frequent and severe, widespread delays, cancellations, and economic losses warrant the need for novel methods that address the limitations of training and management approaches that have changed little for decades. This Faculty Early Career Development Program (CAREER) award supports research that aims to improve how disruptions are anticipated and managed by enabling more proactive training and more practical decision support. This research introduces new ways to use data on rare and severe disruptions together with advanced decision-making methods to identify effective response strategies under uncertainty. By strengthening the resilience and reliability of the air transportation system, this project serves the national interest by reducing economic losses, improving infrastructure performance, and supporting the continued global competitiveness of the United States. Integrated educational and outreach activities will engage students at multiple levels, helping to build a future workforce in aviation and aerospace engineering. This project will establish new theoretical and algorithmic foundations for proactive and practical air traffic disruption management through two integrated research thrusts. The first develops statistically rigorous methods to generate realistic disruption scenario, including rare and extreme events, using extreme event modeling and multivariate distributions that capture nonlinear dependencies among concurrent disruption types (e.g., severe weather, equipment outages, and staffing constraints). These scenarios are paired with an optimization-based formulation that identifies feasible and effective control actions for managing air traffic under degraded conditions. The second thrust advances real-time decision support by introducing practical, multi-utility optimization models that assist air traffic controllers in making operational decisions, such as selecting flights to test uncertain airspace conditions during disruptions, and by developing rapid retrieval of relevant operational knowledge via trained large language models. The research integrates stochastic modeling, optimization, and modern data science techniques into a unified framework that connects scenario-based training with real-time decision support. The methods will be validated and evaluated using progressively complex case studies spanning local airport operations, regional airspace, and national-scale coordination, demonstrating their effectiveness across the entire air transportation system. This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria. NSF Award ID: 2540115 | Program: 01002627DB NSF RESEARCH & RELATED ACTIVIT | Principal Investigator: Max Li | Institution: Regents of the University of Michigan - Ann Arbor, ANN ARBOR, MI | Award Amount: $550,000 View on NSF Award Search: https://www.nsf.gov/awardsearch/show-award/?AWD_ID=2540115 View on Research.gov: https://www.research.gov/awardapi-service/v1/awards/2540115.html