Arrêt de service programmé du vendredi 10 juin 16h jusqu’au lundi 13 juin 9h. Pour en savoir plus
Accéder directement au contenu Accéder directement à la navigation
Article dans une revue

Predictive Distribution of the Mass and Speed Profile to Improve Aircraft Climb Prediction

Abstract : Ground-based aircraft trajectory prediction is a major concern in air traffic management. Focusing on the climb phase, neural networks are trained to predict some of the unknown point-mass model parameters. These unknown parameters are the mass and the speed intent. For each unknown parameter, our model predicts a Gaussian distribution. This predicted distribution is a predictive distribution: it is the distribution of possible unknown parameter values conditional to the observed past trajectory of the considered aircraft. Using this distribution, one can extract a predicted value and the uncertainty related to this specific prediction. This study relies on Automatic Dependent Surveillance-Broadcast data coming from The OpenSky Network. It contains the climbing segments of the year 2017 detected by the network. The obtained data set contains millions of climbing segments from all over the world. Using this data set, it is shown that despite having an error slightly larger than previously tested methods, the predicted uncertainty allows us to reduce the size of prediction intervals while keeping the same coverage probability. Furthermore, it is shown that the trajectories with a similar predicted uncertainty have an observed error close to the predicted one. The data set and the machine learning code are publicly available.
Type de document :
Article dans une revue
Liste complète des métadonnées

Littérature citée [47 références]  Voir  Masquer  Télécharger

https://hal-enac.archives-ouvertes.fr/hal-02904350
Contributeur : Laurence Porte Connectez-vous pour contacter le contributeur
Soumis le : vendredi 24 juillet 2020 - 12:13:00
Dernière modification le : mercredi 3 novembre 2021 - 08:11:53
Archivage à long terme le : : mardi 1 décembre 2020 - 18:19:41

Fichier

jat_alligier_2020.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

Collections

Citation

Richard Alligier. Predictive Distribution of the Mass and Speed Profile to Improve Aircraft Climb Prediction. Journal of Air Transportation, AIAA, 2020, pp.1-10 / ISBN: 978-1-7281-5381-0. ⟨10.2514/1.D0181⟩. ⟨hal-02904350⟩

Partager

Métriques

Consultations de la notice

69

Téléchargements de fichiers

137