Stochastic models of Ground Delay Program implementation for prediction, simulation, and insight
The authors use historical data to build two types of stochastic model of hourly Ground Delay Program (GDP) implementation for the three main airports near New York City: Newark Liberty International, LaGuardia, and John F. Kennedy International. The models predict the probability that a GDP will be initialized or canceled in a given hour based on hundreds of features describing the situation at the airport, including features describing forecasted weather conditions and scheduled traffic. One is a regularized logistic regression model that ignores system dynamics and the other model is based on inverse reinforcement learning, so it considers system dynamics and the impact that GDP implementation actions have over time on some metrics. The authors evaluate the models based on two objectives: their ability to predict and simulate GDP implementation decisions in historical test data sets. As is expected based on the motivation for and objective of each type of model, regularized logistic regression models make superior predictions while simulations controlled by inverse reinforcement learning models produce average metric values that more closely match those produced by historical GDP implementation decisions. Finally, the authors draw insights about GDP implementation from the trained model parameters. For example, parameters of both models suggest while weather conditions and values of performance metrics such as airborne delay play a role in GDP decision making, parameters related to the predictability or continuity of existing GDP plans are also important.
- Record URL:
-
Availability:
- Find a library where document is available. Order URL: http://worldcat.org/issn/2211002X
-
Supplemental Notes:
- ©2017 IOS Press and the authors. All rights reserved.
-
Authors:
- Bloem, Michael
- Bambos, Nicholas
- Publication Date: 2017
Language
- English
Media Info
- Media Type: Web
- Features: Figures; References;
- Pagination: pp 85-117
-
Serial:
- Journal of Aerospace Operations
- Volume: 5
- Issue Number: 1-2
- Publisher: IOS Press
- ISSN: 2211-002X
- EISSN: 2211-0038
- Serial URL: http://iospress.metapress.com/content/122263
Subject/Index Terms
- TRT Terms: Airport surface traffic control; Airports; Flight delays; Implementation; Logistic regression analysis; Simulation; Stochastic processes
- Identifier Terms: John F. Kennedy International Airport; LaGuardia Airport; Newark Liberty International Airport
- Subject Areas: Aviation; Operations and Traffic Management; Planning and Forecasting; Terminals and Facilities;
Filing Info
- Accession Number: 01708261
- Record Type: Publication
- Files: TRIS
- Created Date: Jun 24 2019 10:10AM