Data driven analysis and prediction of traffic and safety disturbances

ELSA aims at developing novel metrics and techniques to analyse and monitor the propagation of disturbances in the ATM system.

PROJECT: ELSA – Empirically grounded agent based models for the future ATM scenario

FUNDING SCHEME: SESAR JU, Workpackage E – Long Term Research

DURATION: 2011-2015 (CLOSED)


ELSA identifies statistical regularities in long time periods – one month to one year – using techniques from Statistical Mechanics and Complex Systems theory. Examples include variations in predictability during the flight execution phase, correlation between traffic and safety metrics, seasonal fluctuations.  Regularities and anomalies are identified at various levels: local, national, EU level.


A second branch of work relates to the development of an Air Traffic Simulator of increasing complexity and degree of realism, to simulate the current scenario and the future SESAR scenarios.


The last strand of work is the design and development of the prototype of a tool to monitor the current complexity status, receive a prediction of the likely development, simulate the effects of changes to the system. The ELSA tool is developed as a proof of concept, visually representing a future data-driven ATM system.



Deep Blue is the project coordinator.


We have designed the overall work concept and approach with our scientific partners of University of Palermo and Scuola Normale Superiore di Pisa, pioneering one of the first data-driven projects in ATM.


We also contribute to the selection of novel metrics and analysis techniques, assessing their operational relevance and expected benefits for SESAR.


We organise and manage the validation activities, defining which future scenarios to test and collecting feedback from operational experts.


  • The ELSA novel metrics and techniques can be used to analyse and monitor the current ATM system at the EU level, processing big amounts of data, and quantitatively measuring the benefits brought by the implementation of SESAR concepts, e.g. integration of sectors in FABs, user-preferred trajectories.
  • We can also measure the degree of optimisation brought by SESAR concepts in normal conditions, including also aspects like the number and type (e.g. tactical vs. planning) of ATCOs’ actions.
  • The ELSA Air Traffic Simulator is a tool capable of testing different future scenarios, for instance by simulating the transition period, when a SESAR concept is being implemented, but not fully deployed. The simulator can be considered as a common platform to be used by the SESAR research community, to make it easier to compare different research programs, or to provide synthetic data for data mining algorithms testing.
  • The ELSA prototype shows how controllers will be able in the future to monitor and intervene on traffic disturbances, including a detailed design of the Human Machine Interface and interaction modalities.

More Projects

Related News

More information?