Abstract: Air traffic managers and flight operators are faced with challenging decisions due to the uncertainty in capacity stemming from variability in weather, demand and human factors. Accurate airport capacity predictions are necessary to develop efficient decision-support tools for air traffic control and for planning effective traffic management initiatives. Capacity of an airport can be observed only at sufficiently large demand. However, if the throughput of an airport is limited by the demand, we can only conclude that the capacity is larger than or equal to the observed throughput. This inability to directly observe capacity makes capacity prediction a challenging and less explored problem.
This work applies machine-learning methods that incorporate observations censored by insufficient demand to develop an airport capacity prediction model. The model predicts a capacity distribution rather than a single capacity value for an hour of interest at an airport using its weather and scheduled demand data. We also discuss validation measures that account for the presence of censored observations. This work explores an important application of the estimated model: to develop capacity-based distance metric between two days using their predicted hourly capacity distributions. For a given reference day, the capacity-based distance can be used to identify similar historical days. The traffic management initiatives taken on past similar days and their resulting outcomes can augment controller experience to guide decision-making on the reference day at an airport.
Bio: Sreeta Gorripaty is a doctoral candidate in the Transportation Engineering program at UC Berkeley. Sreeta received her MS in Transportation Engineering at UC Berkeley and did her undergraduate in Civil Engineering from IIT Bombay. Her research focuses on applying machine learning and statistical methods to improve air traffic management and airport planning. Sreeta received the Graduate Research Award from Airport Cooperative Research Program in 2015 and also won Women's Transportation Seminar (WTS) Legacy Scholarship in 2015.