@techreport{
 title = {Improving the Predictability of Take-off Times with Machine Learning A case study for the Maastricht upper area control centre area of responsibility},
 type = {techreport},
 keywords = {Index Terms-trajectory prediction,machine learning},
 id = {aee8634c-c04c-37aa-a31b-4ac1cb32ffbc},
 created = {2020-02-02T16:52:28.248Z},
 file_attached = {true},
 profile_id = {da21ad65-ce4d-32fc-9adb-84842d41ea94},
 last_modified = {2020-02-02T16:52:31.215Z},
 read = {false},
 starred = {false},
 authored = {true},
 confirmed = {false},
 hidden = {false},
 private_publication = {false},
 abstract = {The uncertainty of the takeoff time is a major contribution to the loss of trajectory predictability. At present, the Estimated TakeOff Time (ETOT) for each individual flight is extracted from the Enhanced Traffic Flow Management System (ETFMS) messages, which are sent each time there is an event triggering a recalculation of the flight data by the Network Manager Operations Centre. However, aircraft do not always takeoff at the ETOTs reported by the ETFMS due to several factors, including congestion and bad weather conditions at the departure airport, reactionary delays and air traffic flow management slot improvements. This paper presents two machine learning models that take into account several of these factors to improve the takeoff time prediction of individual flights one hour before their estimated off-block time. Predictions performed by the model trained on three years of historical flight and weather data show a reduction on the takeoff time prediction error of about 30% as compared to the ETOTs reported by the ETFMS.},
 bibtype = {techreport},
 author = {Dalmau, Ramon and Ballerini, Franck and Naessens, Herbert and Belkoura, Seddik and Wangnick, Sebastian}
}

{"_id":"AjgqJpY6r5ZLSYpAs","bibbaseid":"dalmau-ballerini-naessens-belkoura-wangnick-improvingthepredictabilityoftakeofftimeswithmachinelearningacasestudyforthemaastrichtupperareacontrolcentreareaofresponsibility","authorIDs":["5e36ffcf6568afde01000056"],"author_short":["Dalmau, R.","Ballerini, F.","Naessens, H.","Belkoura, S.","Wangnick, S."],"bibdata":{"title":"Improving the Predictability of Take-off Times with Machine Learning A case study for the Maastricht upper area control centre area of responsibility","type":"techreport","keywords":"Index Terms-trajectory prediction,machine learning","id":"aee8634c-c04c-37aa-a31b-4ac1cb32ffbc","created":"2020-02-02T16:52:28.248Z","file_attached":"true","profile_id":"da21ad65-ce4d-32fc-9adb-84842d41ea94","last_modified":"2020-02-02T16:52:31.215Z","read":false,"starred":false,"authored":"true","confirmed":false,"hidden":false,"private_publication":false,"abstract":"The uncertainty of the takeoff time is a major contribution to the loss of trajectory predictability. At present, the Estimated TakeOff Time (ETOT) for each individual flight is extracted from the Enhanced Traffic Flow Management System (ETFMS) messages, which are sent each time there is an event triggering a recalculation of the flight data by the Network Manager Operations Centre. However, aircraft do not always takeoff at the ETOTs reported by the ETFMS due to several factors, including congestion and bad weather conditions at the departure airport, reactionary delays and air traffic flow management slot improvements. This paper presents two machine learning models that take into account several of these factors to improve the takeoff time prediction of individual flights one hour before their estimated off-block time. Predictions performed by the model trained on three years of historical flight and weather data show a reduction on the takeoff time prediction error of about 30% as compared to the ETOTs reported by the ETFMS.","bibtype":"techreport","author":"Dalmau, Ramon and Ballerini, Franck and Naessens, Herbert and Belkoura, Seddik and Wangnick, Sebastian","bibtex":"@techreport{\n title = {Improving the Predictability of Take-off Times with Machine Learning A case study for the Maastricht upper area control centre area of responsibility},\n type = {techreport},\n keywords = {Index Terms-trajectory prediction,machine learning},\n id = {aee8634c-c04c-37aa-a31b-4ac1cb32ffbc},\n created = {2020-02-02T16:52:28.248Z},\n file_attached = {true},\n profile_id = {da21ad65-ce4d-32fc-9adb-84842d41ea94},\n last_modified = {2020-02-02T16:52:31.215Z},\n read = {false},\n starred = {false},\n authored = {true},\n confirmed = {false},\n hidden = {false},\n private_publication = {false},\n abstract = {The uncertainty of the takeoff time is a major contribution to the loss of trajectory predictability. At present, the Estimated TakeOff Time (ETOT) for each individual flight is extracted from the Enhanced Traffic Flow Management System (ETFMS) messages, which are sent each time there is an event triggering a recalculation of the flight data by the Network Manager Operations Centre. However, aircraft do not always takeoff at the ETOTs reported by the ETFMS due to several factors, including congestion and bad weather conditions at the departure airport, reactionary delays and air traffic flow management slot improvements. This paper presents two machine learning models that take into account several of these factors to improve the takeoff time prediction of individual flights one hour before their estimated off-block time. Predictions performed by the model trained on three years of historical flight and weather data show a reduction on the takeoff time prediction error of about 30% as compared to the ETOTs reported by the ETFMS.},\n bibtype = {techreport},\n author = {Dalmau, Ramon and Ballerini, Franck and Naessens, Herbert and Belkoura, Seddik and Wangnick, Sebastian}\n}","author_short":["Dalmau, R.","Ballerini, F.","Naessens, H.","Belkoura, S.","Wangnick, S."],"urls":{"Paper":"https://bibbase.org/service/mendeley/da21ad65-ce4d-32fc-9adb-84842d41ea94/file/67dfb000-a491-01ff-3fa0-0537385b9522/SIDs_totem.pdf.pdf"},"bibbaseid":"dalmau-ballerini-naessens-belkoura-wangnick-improvingthepredictabilityoftakeofftimeswithmachinelearningacasestudyforthemaastrichtupperareacontrolcentreareaofresponsibility","role":"author","keyword":["Index Terms-trajectory prediction","machine learning"],"downloads":0},"bibtype":"techreport","creationDate":"2020-02-02T16:58:55.433Z","downloads":0,"keywords":["index terms-trajectory prediction","machine learning"],"search_terms":["improving","predictability","take","times","machine","learning","case","study","maastricht","upper","area","control","centre","area","responsibility","dalmau","ballerini","naessens","belkoura","wangnick"],"title":"Improving the Predictability of Take-off Times with Machine Learning A case study for the Maastricht upper area control centre area of responsibility","year":null}