Characterization and prediction of air traffic delays
This paper presents a new class of models for predicting air traffic delays. The proposed models consider both temporal and spatial (that is, network) delay states as explanatory variables, and use Random Forest algorithms to predict departure delays 2–24 h in the future. In addition to local delay...
| Main Authors: | , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | en_US |
| Published: |
Elsevier
2017
|
| Online Access: | http://hdl.handle.net/1721.1/111158 https://orcid.org/0000-0002-8624-7041 |
| _version_ | 1811072450944827392 |
|---|---|
| author | Rebollo De La Bandera, Juan Jose Balakrishnan, Hamsa |
| author2 | Massachusetts Institute of Technology. Department of Aeronautics and Astronautics |
| author_facet | Massachusetts Institute of Technology. Department of Aeronautics and Astronautics Rebollo De La Bandera, Juan Jose Balakrishnan, Hamsa |
| author_sort | Rebollo De La Bandera, Juan Jose |
| collection | MIT |
| description | This paper presents a new class of models for predicting air traffic delays. The proposed models consider both temporal and spatial (that is, network) delay states as explanatory variables, and use Random Forest algorithms to predict departure delays 2–24 h in the future. In addition to local delay variables that describe the arrival or departure delay states of the most influential airports and links (origin–destination pairs) in the network, new network delay variables that characterize the global delay state of the entire National Airspace System at the time of prediction are proposed. The paper analyzes the performance of the proposed prediction models in both classifying delays as above or below a certain threshold, as well as predicting delay values. The models are trained and validated on operational data from 2007 and 2008, and are evaluated using the 100 most-delayed links in the system. The results show that for a 2-h forecast horizon, the average test error over these 100 links is 19% when classifying delays as above or below 60 min. Similarly, the average over these 100 links of the median test error is found to be 21 min when predicting departure delays for a 2-h forecast horizon. The effects of changes in the classification threshold and forecast horizon on prediction performance are studied. |
| first_indexed | 2024-09-23T09:06:09Z |
| format | Article |
| id | mit-1721.1/111158 |
| institution | Massachusetts Institute of Technology |
| language | en_US |
| last_indexed | 2024-09-23T09:06:09Z |
| publishDate | 2017 |
| publisher | Elsevier |
| record_format | dspace |
| spelling | mit-1721.1/1111582022-09-30T13:28:03Z Characterization and prediction of air traffic delays Rebollo De La Bandera, Juan Jose Balakrishnan, Hamsa Massachusetts Institute of Technology. Department of Aeronautics and Astronautics Rebollo De La Bandera, Juan Jose Balakrishnan, Hamsa This paper presents a new class of models for predicting air traffic delays. The proposed models consider both temporal and spatial (that is, network) delay states as explanatory variables, and use Random Forest algorithms to predict departure delays 2–24 h in the future. In addition to local delay variables that describe the arrival or departure delay states of the most influential airports and links (origin–destination pairs) in the network, new network delay variables that characterize the global delay state of the entire National Airspace System at the time of prediction are proposed. The paper analyzes the performance of the proposed prediction models in both classifying delays as above or below a certain threshold, as well as predicting delay values. The models are trained and validated on operational data from 2007 and 2008, and are evaluated using the 100 most-delayed links in the system. The results show that for a 2-h forecast horizon, the average test error over these 100 links is 19% when classifying delays as above or below 60 min. Similarly, the average over these 100 links of the median test error is found to be 21 min when predicting departure delays for a 2-h forecast horizon. The effects of changes in the classification threshold and forecast horizon on prediction performance are studied. National Science Foundation (U.S.) (Award 0931843) National Science Foundation (U.S.) (Award 1239054) 2017-09-08T15:25:25Z 2017-09-08T15:25:25Z 2014-05 2014-04 Article http://purl.org/eprint/type/JournalArticle 0968-090X http://hdl.handle.net/1721.1/111158 Rebollo, Juan Jose and Balakrishnan, Hamsa. “Characterization and Prediction of Air Traffic Delays.” Transportation Research Part C: Emerging Technologies 44 (July 2014): 231–241 © 2014 Elsevier Ltd https://orcid.org/0000-0002-8624-7041 en_US http://dx.doi.org/10.1016/j.trc.2014.04.007 Transportation Research Part C: Emerging Technologies Creative Commons Attribution-NonCommercial-NoDerivs License http://creativecommons.org/licenses/by-nc-nd/4.0/ application/pdf Elsevier MIT Web Domain |
| spellingShingle | Rebollo De La Bandera, Juan Jose Balakrishnan, Hamsa Characterization and prediction of air traffic delays |
| title | Characterization and prediction of air traffic delays |
| title_full | Characterization and prediction of air traffic delays |
| title_fullStr | Characterization and prediction of air traffic delays |
| title_full_unstemmed | Characterization and prediction of air traffic delays |
| title_short | Characterization and prediction of air traffic delays |
| title_sort | characterization and prediction of air traffic delays |
| url | http://hdl.handle.net/1721.1/111158 https://orcid.org/0000-0002-8624-7041 |
| work_keys_str_mv | AT rebollodelabanderajuanjose characterizationandpredictionofairtrafficdelays AT balakrishnanhamsa characterizationandpredictionofairtrafficdelays |