Detecting Events in Aircraft Trajectories: Rule-Based and Data-Driven Approaches †
2. A Taxonomy of Events
3. Rule-Based Methods for Event Detection
3.1. Identification of Missions Based on Tail Numbers
3.2. Identification of Missions Based on Call Sign Information
3.3. Detection of Take-Off and Landing
- The onground flag is rather unreliable; information should be cross-checked with other features;
- Aircraft may land or take off outside designated areas (gliders, helicopters).
3.4. Detection of Events around a Flight Plan
- During a long-haul flight, aircraft sometimes target navigational points that are far ahead, pushing ad hoc criteria to their limits;
- It is difficult to know which point is targeted when they appear nearly aligned (see ERTOKand ERIXUin the red trajectory in Figure 3);
- Flight management systems are able to follow Standard Lateral Offset Procedures (SLOP) during transatlantic flights: they follow a route parallel to the next navigational point, which adds complexity to an automatic rule-based detection procedure.
3.5. Detection of Events during Final Approach
- consider the runway thresholds as targeted navigational points (ILS modelling);
- consider the ground trajectory, and select the part matching the footprint of a runway (taxi modelling).
- VFR (Visual Flight Rule) landing may be harder to detect using the ILS modelling;
- Successive runway alignments (ILS modelling) may suggest a runway change (if the aircraft continuously descends) or a go-around (if the aircraft climbs between the two segments);
- Circle to land manoeuvres yield a different runway with the ILS modelling approach and with the taxi modelling approach.
3.6. Identification of the Flight Phase with Fuzzy Logic
4. Statistical Methods to Detect Specific Patterns
4.1. Runway Changes
- with a rule-based method: segments of trajectories aligned with a runway (ILS modelling) for at least one minute are computed for each flight; we select only trajectories yielding two different alignments without go-around;
- with a statistical method: trajectories, limited to the time series associated with the track angle values, are selected between zero and eight nautical miles before the runway threshold, scaled down to a constant number of samples (resampled), before computing their Karhunen–Loève decomposition ; the first component models the alignment phase with the runway, and we select trajectories with a second and third component—the variation modes associated with a runway change—above the 90th percentile.
- The blue part of the distribution corresponds to runway changes occurring beyond the eight nautical miles where we clipped trajectories for the statistical method. This is not a surprise as the dataset for the statistical method was clipped within eight nautical miles from the runway thresholds.
- The red part of the distribution corresponds to a very late runway change. This suggests that we should probably include the fourth component of the PCA in the criterion.
4.2. Holding Patterns
5. Conclusive Remarks
Conflicts of Interest
- Schultz, M.; Rosenow, J.; Olive, X. A-CDM Lite: Situation Awareness and Decision-making for Small Airports based on ADS-B Data. In Proceedings of the 9th SESAR Innovation, Athens, Greece, 2–5 December 2019; p. 8. [Google Scholar]
- Schultz, M.; Olive, X.; Rosenow, J.; Fricke, H.; Alam, S. Analysis of airport ground operations based on ADS-B data. In Proceedings of the 2020 International Conference on Artificial Intelligence and Data Analytics for Air Transportation (AIDA-AT), Singapore, 3–4 February 2020; p. 9. [Google Scholar]
- Proud, S.R. Go-Around Detection Using Crowd-Sourced ADS-B Position Data. Aerospace 2020, 7, 16. [Google Scholar] [CrossRef]
- Olive, X.; Bieber, P. Quantitative Assessments of Runway Excursion Precursors using Mode S data. In Proceedings of the 8th International Conference for Research in Air Transportation, Barcelona, Spain, 26–29 June 2018. [Google Scholar]
- Olive, X.; Basora, L. Detection and identification of significant events in historical aircraft trajectory data. Transp. Res. Part C Emerg. Technol. 2020, 119, 102737. [Google Scholar] [CrossRef]
- Olive, X. traffic, a toolbox for processing and analysing air traffic data. J. Open Source Softw. 2019, 4, 1518. [Google Scholar] [CrossRef]
- Hernandez, M.; Scarr, S.; Sharma, M. How California Uses Dozens of Aircraft to Battle Wildfires. 2020. Available online: https://graphics.reuters.com/CALIFORNIA-WILDFIRE/AIRCRAFT/bdwpkzmyyvm/ (accessed on 29 November 2020).
- Olive, X.; Tanner, A.; Strohmeier, M.; Schafer, M.; Feridun, M.; Tart, A.; Martinovic, I.; Lenders, V. OpenSky Report 2020: Analysing in-flight emergencies using big data. In Proceedings of the 39th IEEE/AIAA Digital Avionics Systems Conference (DASC), San Antonio, TX, USA, 11–15 October 2020. [Google Scholar]
- Sun, J.; Ellerbroek, J.; Hoekstra, J. Large-Scale Flight Phase Identification from ADS-B Data Using Machine Learning Methods. In Proceedings of the 7th International Conference on Research in Air Transportation, Philadelphia, PA, USA, 20–24 June 2016. [Google Scholar]
- Sun, J.; Hoekstra, J.M.; Ellerbroek, J. OpenAP: An open-source aircraft performance model for air transportation studies and simulations. Aerospace 2020, 7, 104. [Google Scholar] [CrossRef]
|Related Data||Related Works|
|Firefighting operations||fire location, aircraft fleet|||
|Calibration flights||aircraft equipment, runway and VORinformation|
|Rescue operations||aircraft registration, call sign, e.g., SAMU*, LIFE*, REGA*|
|Police operations||aircraft registration, call sign|
|Zero gravity flights||aircraft registration, e.g., F-WNOV(A310), N794AJ (B727)|
|Aerial surveys||aircraft registration|
|Test flights||call sign, e.g., AIB* (Airbus), BOE* (Boeing); aircraft registration|
|Loon balloons||aircraft registration, call sign, e.g., HBAL*|
|Direct to||flight plan, navigational beacons|
|Holding pattern||navigational beacons, emergency information|||
|ILS landing||runway information|
|Refuelling||designated areas, aircraft registration|
|Fuel dumping||safety reports|||
|Runway change, circle to land||runway information|
|Flight phases||including ground phase, climb, descent, cruise and levelling|||
|Hovering||aircraft registration (helicopters or drones)|
Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations.
© 2020 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Olive, X.; Sun, J.; Lafage, A.; Basora, L. Detecting Events in Aircraft Trajectories: Rule-Based and Data-Driven Approaches. Proceedings 2020, 59, 8. https://doi.org/10.3390/proceedings2020059008
Olive X, Sun J, Lafage A, Basora L. Detecting Events in Aircraft Trajectories: Rule-Based and Data-Driven Approaches. Proceedings. 2020; 59(1):8. https://doi.org/10.3390/proceedings2020059008Chicago/Turabian Style
Olive, Xavier, Junzi Sun, Adrien Lafage, and Luis Basora. 2020. "Detecting Events in Aircraft Trajectories: Rule-Based and Data-Driven Approaches" Proceedings 59, no. 1: 8. https://doi.org/10.3390/proceedings2020059008