Advertisement

Semantic-aware aircraft trajectory prediction using flight plans

  • Harris GeorgiouEmail author
  • Nikos Pelekis
  • Stylianos Sideridis
  • David Scarlatti
  • Yannis Theodoridis
Regular Paper
  • 16 Downloads

Abstract

Aircraft trajectory prediction (TP) is a challenging and inherently data-driven time-series modeling problem. Adding annotation or enrichment parameters further increases the search space complexity, especially when ‘blind’ optimization algorithms are employed. In this paper, flight plans, localized weather and aircraft properties are introduced as trajectory annotations that enable modeling in a space higher than the typical 4-D spatio-temporal. A multi-stage hybrid approach is employed for a new variation of the core TP task, the so-called Future Semantic Trajectory Prediction, including clustering the enriched trajectory data using a semantic-aware similarity function as distance metric. Subsequently, a separate predictive model is trained for each cluster, using a nonuniform graph-based grid that is formed by the waypoints of each flight plan. In practice, flight plans constitute a constrained-based training of each predictive model, one for each waypoint, independently. The proposed method is formulated and experimentally validated with real aviation dataset (flight plans and IFS radar tracks) and localized weather data for a 1-month time frame of flights in the Spanish airspace. Various types of predictive models are tested, including hidden Markov model (HMM), linear regressors, regression trees and feed-forward neural networks. The results show very narrow confidence intervals for the per-waypoint TP errors in HMM, while the more efficient linear and nonlinear regressors exhibit 3-D spatial accuracy much lower than the current state of the art, up to a factor of five compared to ‘blind’ TP for complete flights, in the order of 2–3 km compared to the actual flight routes.

Keywords

Trajectory prediction Semantic clustering Big data analytics Regression 

Notes

Acknowledgements

This work was partially supported by the projects \(\textit{datAcron}\) (http://datacron-project.eu/) and \(\textit{DART}\) (http://dart-research.eu/), which have received funding from the European Union’s Horizon 2020 (H2020) program under Grant Agreements No: 687591 and No: 699299, respectively.

References

  1. 1.
    Ankerst, M., Breunig, M., et al.: Optics: ordering points to identify the clustering structure. In: Proceedings of SIGMOD 1999 (1999)Google Scholar
  2. 2.
    Ayhan, S., Samet, H.: Aircraft trajectory prediction made easy with predictive analytics. In: Proceedings of ACM SIGKDD 2016 (2016)Google Scholar
  3. 3.
    Ayhan, S., Samet, H.: Time series clustering of weather observations in predicting climb phase of aircraft trajectories. In: Proceedings of the IWCTS 2016 (2016)Google Scholar
  4. 4.
    Breiman, L., Friedman, J., Olsen, R., Stone, C.: Classification and Regression Trees. CRC Press, Boca Raton (1984)zbMATHGoogle Scholar
  5. 5.
    Chen, L., Ng, R.: On the marriage of edit distance and lp norms. In: Proceedings of VLDB 2004 (2004)Google Scholar
  6. 6.
    Chen, X., Landry, S., Nof, S.: A framework of enroute air traffic conflict detection and resolution through complex network analysis. Comput. Ind. 62(8), 787–794 (2011)CrossRefGoogle Scholar
  7. 7.
    Cheng, T., Cui, D., Cheng, P.: Data mining for air traffic flow forecasting: a hybrid model of neural network and statistical analysis. In: Proceedings of the ITSC 2003 (2003)Google Scholar
  8. 8.
    Ciccio, C.D., var der Aa, H., Cabanillas, C., et al.: Detecting flight trajectory anomalies and predicting diversions in freight transportation. Decis. Support Syst. 88, 1–17 (2016)CrossRefGoogle Scholar
  9. 9.
    Coppenbarger, R.: En route climb trajectory prediction enhancement using airplane flight-planning information. In: American Institute of Aeronautics and Astronautics (AIAA-99-4147) (1999)Google Scholar
  10. 10.
    de Leege, A., Paassen, M.V., Mulder, M.: A machine learning approach to trajectory prediction. In: Proceedings of AIAA GNC 2013 (2013)Google Scholar
  11. 11.
    Enea, G., Poretta, M.: A comparison of 4d-trajectory operations envisioned for nextgen and sesar. In: Proceedings of the ICAS 2012 (2012)Google Scholar
  12. 12.
    Fablec, Y.L., Alliot, J.: Using neural networks to predict aircraft trajectories. In: Proceedings of the ICIS 1999 (1999)Google Scholar
  13. 13.
    Georgiou, H., Karagiorgou, S., Kontoulis, Y., Pelekis, N., Petrou, P., Scarlatti, D., Theodoridis, Y.: Moving objects analytics—survey on future location and trajectory prediction methods. Tech. rep., Data Science Lab, University of Piraeus, Greece (2018). arXiv:1807.04639
  14. 14.
    Gong, C., McNally, D.: A methodology for automated trajectory prediction analysis. In: AIAA Guidance, Navigation, and Control Conference and Exhibit (2004)Google Scholar
  15. 15.
    Hadjaz, A., Marceau, G., Saveant, P., etal.: Online learning for ground trajectory prediction (2012). CoRR arXiv:1212.3998
  16. 16.
    Hamed, M., Gianazza, D., Serrurier, M., Durand, N.: Statistical prediction of aircraft trajectory: regression methods vs point-mass model. In: Proceedings of the ATM 2013 (2013)Google Scholar
  17. 17.
    James, G., Witten, D., Hastie, T., Tibshirani, R.: An Introduction to Statistical Learning with Applications in R. Springer, Berlin (2013)CrossRefzbMATHGoogle Scholar
  18. 18.
    Krumm, J., Horvitz, E.: Predestination: inferring destinations from partial trajectories. In: Proceedings of the UbiComp 2003 (2003)Google Scholar
  19. 19.
    Kuncheva, L.: Combing Pattern Classifiers—Methods and Algorithms. Wiley, Hoboken (2004)CrossRefzbMATHGoogle Scholar
  20. 20.
    Liu, Y., Hansen, M.: Predicting aircraft trajectories: a deep generative convolutional recurrent neural networks approach. Tech. rep., Institute of Transportation Studies, University of California (2018). arXiv:1812.11670
  21. 21.
    Loh, W.: Regression trees with unbiased variable selection and interaction detection. Stat. Sin. 12, 361–386 (2002)MathSciNetzbMATHGoogle Scholar
  22. 22.
    Matsuno, Y., Tachiya, T., Wei, J., et al.: Stochastic optimal control for aircraft conflict resolution under wind uncertainty. Aerosp. Sci. Technol. 43, 77–88 (2015)CrossRefGoogle Scholar
  23. 23.
    Patroumpas, K., Alevizos, E., Artikis, A., Vodas, M., Pelekis, N., Theodoridis, Y.: Online event recognition from moving vessel trajectories. Geoinformatica 21(2), 389–427 (2017)CrossRefGoogle Scholar
  24. 24.
    Pelekis, N., Theodoridis, Y.: Mobility Data Management and Exploration. Springer, Berlin (2014)CrossRefGoogle Scholar
  25. 25.
    Qiu, J., Wu, Q., Ding, G., et al.: A survey of machine learning for big data processing. EURASIP J. Adv. Signal Process. 2016, 67 (2016)CrossRefGoogle Scholar
  26. 26.
    Scarlatti, D.: Dart white paper. Tech. rep., DART—Data-Driven Aircraft Trajectory Prediction Research (H2020) (2017). http://dart-research.eu/2017/04/03/dart-white-paper/
  27. 27.
    Sip, S., Green, S.: Common trajectory prediction capability for decision support tools. In: ATM 5th USA/Europa R&D seminar (2003)Google Scholar
  28. 28.
    Song, Y., Cheng, P., Mu, C.: An improved trajectory prediction algorithm based on trajectory data mining for air traffic management. In: Proceedings of the IEEE ICIA 2012 (2012)Google Scholar
  29. 29.
    Tao, Y., Faloutsos, C., Papadias, D., Liu, B.: Prediction and indexing of moving objects with unknown motion patterns. In: Proceedings of the ACM SIGMOD 2004 (2004)Google Scholar
  30. 30.
    Tastambekov, K., Puechmorel, S., Delahaye, D., et al.: Aircraft trajectory forecasting using local functional regression in sobolev space. Transp. Res. Part C Emerg. Technol. 39, 1–22 (2014)CrossRefGoogle Scholar
  31. 31.
    Theodoridis, S., Koutroumbas, K.: Pattern Recognition, 4th edn. Academic Press, Cambridge (2008)zbMATHGoogle Scholar
  32. 32.
    Thipphavong, D., Schultz, C., et al.: Adaptive algorithm to improve trajectory prediction accuracy of climbing aircraft. J. Guid. Control Dyn. (JGCD) 36(1), 15–24 (2013)CrossRefGoogle Scholar
  33. 33.
    Trasarti, R., Guidotti, R., Monreale, A., Giannotti, F.: Myway: location prediction via mobility profiling. Inf. Syst. 64, 350–367 (2017)CrossRefGoogle Scholar
  34. 34.
    Vouros, G., Pelekis, N., Kravaris, T., Georgiou, H., et al.: Dart—a machine-learning approach to trajectory prediction and demand-capacity balancing. In: 7th SESAR innovation days (SIDs 2017), SESAR (2017)Google Scholar
  35. 35.
    Vouros, G., Vlachou, A., Santipantakis, G., Doulkeridis, C., Pelekis, N., Georgiou, H., et al.: Big data analytics for time critical mobility forecasting - recent progress and research challenges. In: 21st international conference on extending database technology (EDBT 2018), ACM (2018)Google Scholar
  36. 36.
    Vouros, G., Vlachou, A., Santipantakis, G., et al.: Big data analytics for time critical mobility forecasting: recent progress and research challenges. In: Proceedings of the EDBT 2018 (2018)Google Scholar
  37. 37.
    Zheng, Y.: Trajectory data mining: an overview. Trans. Intell. Syst. Technol. 6(3), 1–41 (2015)CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  1. 1.Data Science Lab (datastories.org)University of Piraeus (unipi.gr)AthensGreece
  2. 2.Boeing R&T EuropeMadridSpain

Personalised recommendations