Authors:
Gaetano Zazzaro
;
Francesco Martone
;
Gianpaolo Romano
;
Antonio Vitale
and
Edoardo Filippone
Affiliation:
CIRA (Italian Aerospace Research Centre), Via Maiorise snc, Capua (CE), Italy
Keyword(s):
Data Driven, Data Mining, Machine Learning, Trajectory Prediction, Uncertainties.
Abstract:
This paper presents a data-driven methodology, named P4T, for the trajectory prediction from long to short term before scheduled time of flight, developed within the framework of the PIU4TP project. The methodology is aimed to support the Network Manager in the air traffic flow and capacity management, allowing the optimization of flight distribution among sectors and flight routes, the anticipation of air traffic flow requests and the identification in advance of potential conflicts. The proposed approach applies machine learning and data mining techniques to perform data analysis and to correctly identify, from historical data, the aircraft expected behaviour, in terms of flight path selection. The main peculiarity of this approach is the exploitation of the uncertainties on current forecasts of some relevant mission and aircraft parameters to compute trajectory prediction outcomes enriched with associated probabilistic information. The preliminary validation of the methodology usi
ng simulated data highlighted very promising results.
(More)