Trajectory Clustering for Air Traffic Categorisation
Bolic, T., Castelli, L., De Lorenzo, A. and Vascotto, F. 2022. Trajectory Clustering for Air Traffic Categorisation. Aerospace. 9 (5) 227. https://doi.org/10.3390/aerospace9050227
Bolic, T., Castelli, L., De Lorenzo, A. and Vascotto, F. 2022. Trajectory Clustering for Air Traffic Categorisation. Aerospace. 9 (5) 227. https://doi.org/10.3390/aerospace9050227
Title | Trajectory Clustering for Air Traffic Categorisation |
---|---|
Type | Journal article |
Authors | Bolic, T., Castelli, L., De Lorenzo, A. and Vascotto, F. |
Abstract | Availability of different types of data and advances in data-driven techniques open the path to more detailed analyses of various phenomena. Here, we examine the insights that can be gained through the analysis of historical flight trajectories, using data mining techniques. The goal is to learn about usual (or nominal) choices airlines make in terms of routing, and their relation with aircraft types and operational flight costs. The clustering is applied to intra-European trajectories during one entire summer season, and a statistical test of independence is used to evaluate the relations between the variables of interest. Even though about half of all flights are less than 1000 km long, and mostly operated by one airline, along one trajectory, the analysis shows that, for longer flights, there exists a clear relation between the trajectory clusters and the operating airlines (in about 49% of city pairs) and/or the aircraft types (30%), and/or the flight costs (45%). |
Keywords | trajectory clustering |
DBSCAN | |
airline choice | |
Article number | 227 |
Journal | Aerospace |
Journal citation | 9 (5) |
ISSN | 2226-4310 |
Year | 2022 |
Publisher | MDPI |
Publisher's version | License CC BY 4.0 File Access Level Open (open metadata and files) |
Digital Object Identifier (DOI) | https://doi.org/10.3390/aerospace9050227 |
Web address (URL) | https://www.mdpi.com/2226-4310/9/5/227 |
Publication dates | |
Published online | 21 Apr 2022 |