Detección de anomalías en trayectorias de vuelo utilizando autoencoders y segmentación del espacio aéreo basada en regiones de Voronoi

José David Ortega Pabón; Jimmy Anderson Flórez Zuluaga; Mónica Patricia Hernández Lordui

doi:10.24054/rcta.v1i45.3496

Authors

José David Ortega Pabón Universidad Pontificia Bolivariana https://orcid.org/0000-0002-2743-9422
Jimmy Anderson Flórez Zuluaga Institución Universitaria de Envigado https://orcid.org/0000-0002-0426-1000
Mónica Patricia Hernández Lordui University of Massachusetts Amherst https://orcid.org/0000-0002-9952-2890

DOI:

https://doi.org/10.24054/rcta.v1i45.3496

Keywords:

anomaly detection, autoencoder, machine learning, unsupervised learning, voronoi regions

Abstract

Given the increasing global air traffic, this article compares two autoencoder approaches for anomaly detection in flight trajectories, using the DBSCAN algorithm as an initial reference. The first model utilizes normalized continuous features (latitude, longitude, speed, and heading), while the second incorporates a discrete segmentation of the airspace through Voronoi regions, alongside kinematic variables. The results indicate on average 96% accuracy for the continuous autoencoder and 97% for the Voronoi-based model, with the latter showing a greater ability to identify normal trajectories. Qualitative analysis revealed that autoencoders, by including additional variables, capture more complex anomalies than DBSCAN. The integration of Voronoi regions improved the model's explainability, facilitating the interpretation of anomalies within their geographic context.

Downloads

Download data is not yet available.

References

R. H. Cáceres León, “Meteorología aplicada a la seguridad de las operaciones aéreas,” Ciencia y Poder Aéreo, Jun. 2017, doi: https://doi.org/10.18667/9789585996113.

J. Ortega, J. Florez, S. Lorduy, G. Jimenez, and O. Quintero, “Improve decision-making process in Air Command and Control Systems with meteorological data fusion,” in 2021 International Conference on Decision Aid Sciences and Application (DASA), IEEE, Dec. 2021, pp. 636–642. doi: 10.1109/DASA53625.2021.9682330.

J. Mendling, C. Di Ciccio, H. van der Aa, C. Cabanillas, and J. Prescher, “Detecting flight trajectory anomalies and predicting diversions in freight transportation,” Decis Support Syst, 2016, doi: 10.1016/j.dss.2016.05.004.

M. Ahmed, A. Naser Mahmood, and J. Hu, “A survey of network anomaly detection techniques,” Journal of Network and Computer Applications, vol. 60, pp. 19–31, Jan. 2016, doi: 10.1016/j.jnca.2015.11.016.

R. A. Ariyaluran Habeeb, F. Nasaruddin, A. Gani, I. A. Targio Hashem, E. Ahmed, and M. Imran, “Real-time big data processing for anomaly detection: A Survey,” Int J Inf Manage, vol. 45, no. February, pp. 289–307, Apr. 2019, doi: 10.1016/j.ijinfomgt.2018.08.006.

M. E. Villa-Pérez, M. Á. Álvarez-Carmona, O. Loyola-González, M. A. Medina-Pérez, J. C. Velazco-Rossell, and K.-K. R. Choo, “Semi-supervised anomaly detection algorithms: A comparative summary and future research directions,” Knowl Based Syst, vol. 218, p. 106878, Apr. 2021, doi: 10.1016/j.knosys.2021.106878.

L. Coelho e Silva and M. C. R. Murça, “A data analytics framework for anomaly detection in flight operations,” J Air Transp Manag, vol. 110, Jul. 2023, doi: 10.1016/j.jairtraman.2023.102409.

M. Aksoy, O. Ozdemir, G. Guner, B. Baspinar, and E. Koyuncu, “Flight trajectory pattern generalization and abnormal flight detection with generative adversarial network,” in AIAA Scitech 2021 Forum, American Institute of Aeronautics and Astronautics Inc, AIAA, 2021, pp. 1–11. doi: 10.2514/6.2021-0775.

X. Olive and L. Basora, “Detection and identification of significant events in historical aircraft trajectory data,” Transp Res Part C Emerg Technol, vol. 119, Oct. 2020, doi: 10.1016/j.trc.2020.102737.

M. Memarzadeh, B. Matthews, and T. Templin, “Multiclass Anomaly Detection in Flight Data Using Semi-Supervised Explainable Deep Learning Model,” Journal of Aerospace Information Systems, vol. 19, no. 2, pp. 83–97, Feb. 2022, doi: 10.2514/1.I010959.

A. Chevrot, A. Vernotte, and B. Legeard, “CAE: Contextual auto-encoder for multivariate time-series anomaly detection in air transportation,” Comput Secur, vol. 116, May 2022, doi: 10.1016/j.cose.2022.102652.

M. Y. Pusadan, J. L. Buliali, and R. V. Hari Ginardi, “Cluster Phenomenon to Determine Anomaly Detection of Flight Route,” Procedia Comput Sci, vol. 161, pp. 516–526, 2019, doi: 10.1016/j.procs.2019.11.151.

S. J. Corrado, T. G. Puranik, O. P. Fischer, and D. N. Mavris, “A clustering-based quantitative analysis of the interdependent relationship between spatial and energy anomalies in ADS-B trajectory data,” Transp Res Part C Emerg Technol, vol. 131, Oct. 2021, doi: 10.1016/j.trc.2021.103331.

Jose Ortega, Jimmy Florez, Mónica Hernández, and Jhon Escobar, “Trajectory Validation for Decision Making in Air. Traffic Management Using Voronoi Diagram,” Journal of Artificial Intelligence and Soft Computing Research, vol. 12, no. 4, 2022, [Online]. Available: https://www.webology.org/data-cms/articles/20230215105345pmWEBOLOGY%2019%20(6)%20-%20164.pdf

M. Ester, H.-P. Kriegel, J. Sander, and X. Xu, “A density-based algorithm for discovering clusters in large spatial databases with noise,” in Proceedings of the Second International Conference on Knowledge Discovery and Data Mining, in KDD’96. AAAI Press, 1996, pp. 226–231.

Unidad Administrativa Especial de la Aeronáutica civil (organization), “ENR 3.2 RUTAS ATS SUPERIORES ENR 3.2 UPPER ATS ROUTES,” Aug. 2024, Accessed: Sep. 20, 2024. [Online]. Available: https://www.aerocivil.gov.co/servicios-a-la-navegacion/servicio-de-informacion-aeronautica-ais/Documents/AIP%20AMDT%2065_23/ENR/ENR%203.2.pdf