Data Analytics for Trajectory Selection and Preference-Model Extrapolation in the European Airspace

  • Carlo LanciaEmail author
  • Luigi De Giovanni
  • Guglielmo Lulli
Conference paper
Part of the Operations Research Proceedings book series (ORP)


Representing airspace users’ preferences in Air Traffic Flow Management (ATFM) mathematical models is becoming of high relevance. ATFM models aim to reduce congestion (en-route and at both departure and destination airports) and maximize the Air Traffic Management (ATM) system efficiency by determining the best trajectory for each aircraft. In this framework, the a-priori selection of possible alternative trajectories for each flight plays a crucial role. In this work, we analyze initial trajectories queried from Eurocontrol DDR2 data source. Clustering trajectories yields groups that are homogeneous with respect to known (geometry of the trajectory, speed) and partially known or unknown factors (en-route charges, fuel consumption, weather, etc.). Associations between grouped trajectories and potential choice-determinants are successively explored and evaluated, and the predictive value of the determinants is finally validated. For a given origin-destination pair, this ultimately leads to determining a set of flight trajectories and information on related airspace users’ preferences.


Air traffic flow management Data analytics Mathematical models Airspace users’ preferences 


  1. 1.
    Delgado, L.: European route choice determinants. In: Eleventh USA/Europe Air Traffic Management Research and Development Seminar (2015)Google Scholar
  2. 2.
    Djeumou Fomeni, F., Lulli, G., Zografos, K.G.: An optimization model for assigning 4D-trajectories to flights under the TBO concept. In: Twelfth USA/Europe Air Traffic Management Research and Development Seminar (2017)Google Scholar
  3. 3.
    Eurocontrol: DDR2 Reference Manual (2014)Google Scholar
  4. 4.
    Fernández, E.C., Cordero, J.M., Vouros, G., Pelekis, N., Kravaris, T., Georgiou, H., Fuchs, G., Andrienko, N., Andrienko, G., Casado, E., Scarlatti, D.: DART: a machine-learning approach to trajectory prediction and demand-capacity balancing. In: SESAR Innovation Days, Belgrade, pp. 28–30, November 2017Google Scholar
  5. 5.
    Gariel, M., Srivastava, A.N., Feron, E.: Trajectory clustering and an application to airspace monitoring. IEEE Trans. Intell. Transp. Syst. 12(4), 1511–1524 (2011)CrossRefGoogle Scholar
  6. 6.
    Liu, Y., Hansen, M., Lovell, D.J., Chuang, C., Ball, M.O., Gulfing, J.M.: Causal analysis of en route flight inefficiency - the US experience. In: Twelfth USA/Europe Air Traffic Management Research and Development Seminar (2017)Google Scholar
  7. 7.
    SESAR: The roadmap for delivering high performing aviation for Europe. European ATM Master Plan. Executive view. Edition (2015)Google Scholar
  8. 8.
    Sherali, H.D., Smith, J.C., Trani, A.A.: An airspace planning model for selecting flightplans under workload, safety, and equity considerations. Transp. Sci. 36(4), 378–397 (2002)CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Carlo Lancia
    • 1
    Email author
  • Luigi De Giovanni
    • 2
  • Guglielmo Lulli
    • 3
  1. 1.Mathematical Institute Leiden UniversityLeidenThe Netherlands
  2. 2.Università degli studi di PadovaPadovaItaly
  3. 3.Lancaster University Management SchoolBailrigg, LancasterUK

Personalised recommendations