About - TADA - Terminal Airspace Digital Assistant

Context

Terminal Airspaces (TMA) play a key role in air traffic management (ATM), especially in regions with multiple airports operating in close proximity, known as Multi-Airport Systems (MAS). These areas are among the most complex for air traffic control (ATC) due to the high volume of flights arriving, departing, and transiting through the same airspace. As air traffic continues to grow, managing these busy airspaces efficiently becomes increasingly challenging.

Recent data shows that air traffic in Europe during the summer of 2023 reached 93% of pre-pandemic levels, with some areas exceeding those figures. Forecasts predict that by mid-2024, air traffic will return to pre-pandemic levels and continue to increase in the years ahead. This growth places additional pressure on TMAs, requiring innovative solutions to maintain safety, efficiency, and environmental sustainability.

Methodology

The TADA project follows a structured approach to develop and validate our Terminal Airspace Digital Assistant. The methodology consists of four main key steps:

A: Literature Review

TADA will review existing tools and solutions related to TMAs, sequencing techniques, and air traffic control support tools. The focus is on AI and Machine Learning (ML)-based approaches, including those developed outside the aviation sector to encourage innovative ideas. This approach will help identify gaps in current technologies and guide the project’s advancements. The review will include peer-reviewed academic papers, conference proceedings, and patents to ensure a comprehensive understanding of the latest developments.

B: Operational Services, Environment and Requirement Definition

The project will identify specific use cases for TADA. A list of potential scenarios will be developed and presented to air traffic controllers and industry experts in dedicated workshops to gather feedback. This input will be used to define the operational environment of TADA, detailing its functions, benefits, and user responsibilities. Additionally, workshops will help capture technical and Human-Machine Interface (HMI) requirements, which will guide the system’s development.

C: Data Gathering and Pre-Processing

The TADA Solution will be trained with augmented data that is based on historical operational datasets from ENAV. By processing data (AMAN sequencing data, flight plan data, surveillance data, etc.) in operationally relevant scenarios, the project will ensure the assistance operationally valid.

D: Design and Implementation of the Terminal Airspace Digital Assistant

Once the necessary data is collected and the operational requirements are established, the Team will focus on designing and implementing ML algorithms that support air traffic controllers in decision-making. The system will also improve AMAN sequencing using AI techniques. Moreover, TADA will design the user interface to ensure that AI-generated recommendations are presented in a clear and user-friendly manner. Development will follow an agile process, allowing continuous improvements based on testing and feedback

E: Validation of Terminal Airspace Digital Assistant

A three-step validation process will be carried out:

1) Stakeholder workshops to validate the functional, operational and HMI requirements mainly with end-users (i.e., ATCOs), but also with other relevant stakeholders.

2) Low-Fidelity Simulation focusing on TADA HMI mock-up validation.

3) Human-in-the-loop Real Time Simulation in which ATCOs will be able to interact with TADA prototype in relevant operational scenarios.

All these steps will be essential to reach the project goal and understand if and how TADA can support beyond current Arrival Manager (AMAN) capabilities in terms of ATCO decision-support and performance.