Predicting Aircraft Descent Length with Machine Learning - ENAC - École nationale de l'aviation civile Accéder directement au contenu
Communication Dans Un Congrès Année : 2016

Predicting Aircraft Descent Length with Machine Learning


Predicting aircraft trajectories is a key element in the detection and resolution of air traffic conflicts. In this paper, we focus on the ground-based prediction of final descents toward the destination airport. Several Machine Learning methods – ridge regression, neural networks, and gradient-boosting machine – are applied to the prediction of descents toward Toulouse airport (France), and compared with a baseline method relying on the Eurocontrol Base of Aircraft Data (BADA). Using a dataset of 15,802 Mode-S radar trajectories of 11 different aircraft types, we build models which predict the total descent length from the cruise altitude to a given final altitude. Our results show that the Machine Learning methods improve the root mean square error on the predicted descent length of at least 20 % for the ridge regression, and up to 24 % for the gradient-boosting machine, when compared with the baseline BADA method.
Fichier principal
Vignette du fichier
icrat2016.pdf (675.36 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-01353960 , version 1 (16-08-2016)


  • HAL Id : hal-01353960 , version 1


Richard Alligier, David Gianazza, Nicolas Durand. Predicting Aircraft Descent Length with Machine Learning. ICRAT 2016, 7th International Conference on Research in Air Transportation, FAA, Jun 2016, Philadelphia, United States. ⟨hal-01353960⟩
489 Consultations
441 Téléchargements


Gmail Facebook X LinkedIn More