EUROCONTROL Air Transport Innovation Network

Developing agile digital solutions and services to fit our stakeholders' needs.


At EUROCONTROL, we are transforming the way we connect and serve the operational stakeholders in the air transport domain.

Our new and improved approach is to work closer with the end-users such as air navigation service providers (ANSPs), airports and airspace users to develop agile digital solutions and services in response to their needs. To do this, we have set up the EUROCONTROL Air Transport Innovation Network and innovation projects supported by agile innovation processes.

Our innovation projects aim at developing solutions to selected operational challenges/needs with quantifiable efficiency gains for operational stakeholders.

Development process

The solutions are developed following an agile approach with three key steps:

  • Connect
    Capture operational challenges and needs provided by our stakeholders via an open call and select the challenges to be addressed;
  • Build
    Work on solutions for selected operational challenges and needs in a 6 to 12-month timeframe;
  • Promote
    Communicate the output of the prototyping to promote the solutions and launch the next call for operational challenges.

We are regularly launching new calls for operational challenges. You can find the most recent information here.

EATIN Promote Event 2023

In May 2023, we hosted around 100 experts from 40 organisations and 20 countries at the EUROCONTROL Innovation Hub in Brétigny for the EUROCONTROL Air Transport Innovation Network (EATIN) "Promote" event. The aim was to announce a new batch of projects and showcase the latest prototypes.


New call for operational challenges for our user-driven innovation projects


The outcome of a successful innovation project will be the demonstration of a viable solution.

Our new innovation process is complementary to the SESAR programme and its aspiration to accelerate the market uptake building on existing network of partnerships.

First cycle of pilot solutions

Curfew collaborative management

The product developed within this project uses machine-learning techniques to predict potential curfew infringements for a given flight at a given airport, and has been integrated into EUROCONTROL’s MIRROR platform. Internal testing is currently underway, with the evaluation of the tool to be continued by airport and airlines stakeholders from May 2021. Deployment is planned for 2021.

Dashboard of airborne delays

This project, initiated by airlines, aims at supporting fuel planning by providing information regarding airborne delays at arrival (i.e. in the terminal area) resulting from holding and sequencing. We have developed a dashboard of historical airborne delays (also denoted ASMA additional times) for the top 27 European airports, complemented by a view of the historical and current traffic demand. We are now investigating the feasibility of providing the current and predicted values of airborne delays, and later weather information. Four airlines are following the development: Air Europa, Swiss, Transavia and Turkish Airlines.

Forecast of the ATFM delay evolution for a regulated flight

The project has developed a prototype tool which uses AI to better forecast delays. It provides airlines with a set of indicators, including ATFM delay evolution trend and predicted delay, that should deliver economic, operational and passenger experience benefits.

Second cycle of solutions


The objective of the project was to improve the operational performance through the development of a predictive tool providing pre-tactical and tactical predictions of in-block and off-block time deviations supported by predictions on passenger demand (load factors). We used the Power BI dashboard to visualise the outputs of the model and overall predictions at flight level. The predictive model and the dashboard designed for Geneva Airport have been validated through an operational trial, whose objective was to evaluate the accuracy of the model and to check the dashboard usability from an operational perspective. The project members concluded that the validation results form a very good basis to continue the development by reworking the algorithms focusing mainly on in-block time predictions as well as on revising the layout of the dashboard.

This is one of the first projects that are part of our Air Transport Innovation Network to hand out the prototype for industrialisation. Its objective is to improve the information exchanged between different operational partners – airports, airlines, ground handlers and the EUROCONTROL Network Manager. The project is addressing challenges such as multiple point-to-point data interfaces between airlines, airports and ground handlers; airport to airport data exchange; security aspects regarding the exchanged data, etc. The project team has built a data exchange platform covering flight related data relevant to planning and operations with a standard SWIM data interface. EUROCONTROL is now making the documentation publicly available to the market, so that commercial providers can use it to further develop the platform as a product.

This process innovation project delivered a comprehensive approach to quantify the runway collision barrier model. Using the Network Manager Safety Functions Map (SAFMAP) comprehensive barrier model, the project researched and validated an approach to characterise and quantify the individual barriers success and failure rates and to integrate these into an overall risk and resilience quantitate model. The approach allows users to investigate model sensitivities to changes in the traffic conditions and to analyse the effects of addressing specific risk. A great benefit from using the approach is the ability to explicitly predict safety benefits of new investments – new infrastructure, procedures, or training.

Airspace users

Driven by the requirements of participating airspace users, the project identified operational benefits to having advance notice of the predicted runway in use and runway configuration at an arrival airport. The intended consumers are flight dispatchers (for flight planning purposes, both strategic and pre-tactical), and flight crew (for situational awareness in the tactical phase). Nevertheless, it is envisioned that this tool could also serve (with minimal adaptation) other stakeholders in the operational context. Some of the benefits include: contributing to the calculation of optimal flight route, increasing the predictability of tactical route adjustments related to the runway in use, better estimation of fuel and taxi-times, increased situational awareness, and shared level of information between flight crew and the airline’s dispatchers. Over several months in 2021/22 the project undertook to develop a proof of concept, which was subsequently demonstrated to the participating airlines.


This project, initiated by Paris CDG airport, aims at going a step further to the current operations, with a runway allocation minimizing CO2 emissions for both the airborne and the taxi parts. Thales developed a prototype version of the current arrival manager with this new optimisation feature, fed by detailed fuel data tables (per runway, flow and additional time) developed by EUROCONTROL. The follow’up will be decided by Paris CDG.

The project objective is to visualise predicted knock-on delay and the impact on traffic demand for the next 12h from an FMP, Airport and Airline perspective.

Knock-on delays are mostly caused by aircraft rotations, i.e. a late inbound arrival of an aircraft causing a late departure on the next flight operated by the same aircraft. A smaller share of knock-on delays is caused by connecting passengers, crew, or cargo.

The project targets knock-on delays caused by the aircraft rotations and uses the calculations done by iDEMAND (based on business rules) and the RNN (Night Curfew) models to predict the impact of knock-on delays on the demand picture for FMPs, airports and airlines.

The project aims to create a real-time Decision-Making Support tool:

  • For FMPs, the new interface allows to visualise the predicted demand vs. the ETFMS demand (Airspace or Traffic Volume Set) and to identify if/when knock-on delay will dissipate traffic demand peaks rendering the use of ATFM Regulations unnecessary. Or the opposite, when knock-on delays will cause traffic peaks which are not yet visible in ETFMS.
  • For airports, the new interface allows to visualise the predicted arrival demand vs. the scheduled demand to identify if/when knock-on delays will shift scheduled peaks with an indication of the predicted arrival delay for each individual flight.
  • For airlines, the new interface allows to visualise the predicted departure delay for each flight using a weighing indicator taking the varying degrees of importance (length of delay, aircraft type, seat capacity) into account. The interface also visualises systemic reactionary delays in the airline network caused by suboptimal flight schedules and planning, i.e. identify lack of schedule resilience.

Third cycle of solutions


This project has developed a tool that uses AI to verify the performance of military aircraft during the approach and landing phase of the flight in order to demonstrate the compliance of military capabilities on board the aircraft, namely GPS Precise Positioning System (GPS PPS) receivers. The tool delivers the necessary performance metrics to support certification-qualification processes for military aircraft, contributing to reducing costs, enhancing airport access and capacity, and reducing environmental impact. Stakeholders involved: UK Ministry of Defence (UK MOD).

The Flexible Use of Airspace (FUA) concept provides the European ATM system with the potential to increase the efficiency of airspace usage through enhanced civil-military cooperation. The Military Aviation Authorities’ representatives consider that, in addition to their efforts to alleviate the impact of airspace segregations on civil traffic, the Aircraft Operators (AO) could improve their taking upon the airspace usage opportunities made available throughout FUA.

Furthermore, latest performance reports show room for improvement to filing/re-filing the most horizontally efficient route plan given the state of airspace availability for the duration of the flight.

Before addressing improvement solutions, it is essential to assess in depth both FUA and non-FUA barriers to AO in better exploiting airspace availability opportunities. To that end, the factors and criteria driving AO flight planning and execution need to be captured and understood. Only the results of such an exercise could drive the identification and development of a quick-win digital solution(s) for improving CURA as sought-after by the EATIN programme.

A qualitative study report will provide conclusions and recommendations to alleviate the identified CURA barriers in areas such as procedures, system support, and civil-military cooperation.


The project aims to create a tool that automatically assesses the stand capacity available in an airport’s network to improve stakeholders’ common situational awareness to manage situations related to massive diversions. The main challenges this project addresses include:

  • Heavy capacity reduction can cause massive diversions:
    • Flights already airborne to alternate airports.
    • Possible over-deliveries to other airports, if more than two flights expected.
    • Apron congestion and possible safety issues.
  • Coordination process is commonly performed manually and involves:
    • Surrounding airports to provide apron capacity.
    • Different ATC units, to coordinate with pilots and handle diverted traffic accordingly.
    • Pilots and airlines, to decide where to divert and FPL changes if needed.

Stakeholders involved:
SAS, Swiss, Vueling
CVUT Prague, Euro Jet
AENA, Aeroporti di Roma, SEA Milan

Fourth cycle of solutions

Airspace users

Due to a late arrival of the previous leg a flight can suffer a knock-on delay, and worse, it may be then pushed into a regulation, giving it an additional delay. Using real time data, KORI will calculate the total delay that will affect the flight and explore the delays that would be incurred using alternative routes. In this way, KORI will support the AUs to plan their fleet taking in consideration the network impact on their flights. Participating airlines: Vueling, Swiss and Transavia.

Proposed by Vueling, the project has emerged due to the need of airspace users and airports to have a better predictability of the periods of diversion due to weather events. Nowadays, the information on the periods of diversion is very limited for the airspace users and airports, raising high uncertainty on the operations management throughout the day when the weather gets worse. Stakeholders do not have any tool to know which is the probability for a given flight to be diverted in terms of weather (METAR, TAFOR and/or WIND). It is proposed to develop and validate an AI model to predict the likelihood and trend of diversion, in order to avoid diverted flights (change scheduled flight or delay the flight), avoid undesirable delays for the next flights and avoid unexpected high workload to the Handling Services at another airport. Particpants: Vueling, Transavia, Swiss, Air Europa, Prague airport, Istanbul airport, EBAA.


An impact analysis performed by EUROCONTROL assessed that the total airport ground delay represents a cost of 660 M€ per annum over the ECAC area. It is nowadays commonly recognised that the ATFM world lacks visibility on what happens between in-block and off-block although ground delay might propagate over the network.

The OpTT (Optimisation of Turnaround Times) project uses Machine Learning to predict turnaround duration at CDM airports, with the aim of:

  • assessing the risk of potential ground delay,
  • improving TOBT predictability
  • validating the methodologies at Prague, Geneva and possibly Swedavia airports, and
  • disseminating the methodology to other European airports when required.

The project was initiated by Prague Airport and EUROCONTROL, with a robust cooperation of ANS CZ, Swiss Air Lines, Geneva and Swedavia Airports. Expected time of delivery after validation: Jan 2023.

Proposed by Istanbul Airport, the objective of this project is to establish a real-time communication of the delay reasons.

In 2021 the average departure delay (against the scheduled time) was 9.2mins/flight with ATFM delays contributing 0.8mins/flight. The length of delays is already shared in real-time through the EUROCONTROL MIRROR and NORTI portals but apart from ATFM delays (9% of total delay) there is no real-time sharing of the reasons for delay.

If delayed, flights are more likely to have been affected by non-ATFM delays (e.g. baggage loading, security checks, late fuelling, de-icing, etc.) with little real-time visibility to airport operators, ANSPs and the EUROCONTROL Network Manager on the reasons for these delays. Having a real-time insight into the delay reasons improves the situational awareness across the different actors and allows them to react during the operational day. The real-time sharing of the delay information in a centralised manner would allow for the tactical management of staff and resources adjusted to the actual operational situation. This allows early identification of disruptions at outstations potentially impacting the operation and at the same time centralises the collection of delay reasons to be used for post-ops performance analysis.

IATA has released a new delay code schema (AHM732) in 2022 composed of three digits representing the Turnaround Process, Reason and Stakeholder causing a delay. Sharing the IATA AHM732 Process layer information in real-time amongst operational stakeholders will provide the required insight in the delay drivers. The Process layer information does not disclose airline sensitive delay reasons or information on stakeholders.

Fifth cycle of solutions


The project was proposed by Austrian and ANS CR during the fifth EUROCONTROL Air Transport Innovation Network (EATIN) cycle, in December 2022.

Estimated time of arrival (ETA) is important for all aviation stakeholders because it is an input into various air traffic management (ATM) processes, during several flight phases, starting from the moment the flight plan is submitted up to the moment the flight departs.

A model will be developed to make improved predictions of ETA, the aim of which will be to reduce the average error of current ETA predictions for the different flight phases for a given flight. This model will take the outputs from machine learning models that already exist, which were build and validated within the EATIN programme to address other operational problems. One such example is the FADE model, which is available operationally, and which is used for predicting ATFCM delay of flights. The other models that will be used as inputs come from the KORI and TITOP projects. A new machine learning model may also be developed to improve the prediction of the flight time; its output would be an input into the model for predicting the ETA.

A scoping study reported its findings in May 2023 to stakeholders, and the project is expected to launch in summer 2023.

Stakeholders involved:
Austrian, KLM, Swiss International Air Lines, TAP Air Portugal
Brussels, Heathrow, Prague airports

In today operations, users are limited to non-dynamic taxi times (Default and Variable for CDM airports; static for non-CDM airports), not considering the weather and works at the airport. Users are generally informed a few hours before departure/arrival about the stand allocation and the runway in use.

This lack of information and dynamicity in the taxi times leads to over-fuel estimation for airlines and inefficient planning of resources (stands allocation, ground-handlers availability, etc.)

The TITOP project was proposed by Swiss and it started in January 2023. It emerged based on the need of users to have a more accurate prediction of Taxi Time (TT) that is necessary between landing and stand arrival for an Arrival flight and between stand and take-off for a Departure flight.

For better estimation of the runway in use for the prediction of taxi times, this project is associated to the Prediction of Runway in Use (PRIU) project that aims at improving the prediction of the runway in use depending on weather information.

Stakeholders involved:
Austrian, Vueling, SunExpress, Swiss
Brussels, Heathrow, IGA Istanbul, Paris Aéroport, Prague airports


The HAWAII project was proposed by iGA Istanbul Airport and selected in the 5th cycle of the EUROCONTROL Air Transport Innovation Network in December 2022.

The team at the EUROCONTROL Innovation Hub developed a set of 3 machine learning models providing the stakeholders with accurate estimates of the impact of adverse weather conditions on airport capacity (arrival & departure capacity and probability of an ATFM regulation), based on the last weather forecast available (live TAF).

The project caught the attention of:

  • 6 other major airports: Paris (CDG & Orly), London Heathrow, Prague, Amsterdam Schiphol, Brussels and Zurich
  • 4 airlines: Turkish Airlines, Swiss, Transavia and Vueling, and
  • 3 ANSPs: Czech Republic (ANS CR), Finland (FinTraffic) and Switzerland (Skyguide).

They all decided to participate in the trials that kicked off in August 2023 and will last until February 2024 to cover various weather conditions.

By using the models, airports could avoid underestimation of capacity in case of adverse weather, and so force less flights to wait in holding stacks; while airlines could have a better visibility on the impact of weather at the operated airports.


Contact us to learn more about the project and the application process or check out this article for the latest info.