The solution is designed to enhance human–machine collaboration in the air traffic control environment. It focuses on establishing shared understanding of the traffic situation and lays the groundwork for further ML-based automation in air traffic management.

At its core, the system gathers high-integrity information through aeronautical information exchange models. This information is used to construct a comprehensive knowledge graph that accurately represents the traffic situation at either a sector or ACC level. The system goes beyond compiling factual data by incorporating a knowledge-based system that manages and executes rule-based knowledge through a reasoning engine operating on top of the factual data.

Integral to the system are multiple machine-learning modules capable of assessing probabilistic events, such as trajectory prediction or conflict detection. By combining the reasoning engine with machine learning, the system can analyse complex interactions between objects, draw informed conclusions, explain the reasoning behind these conclusions, and anticipate future system states.

The system significantly enhances safety in air traffic control by reliably performing monotonous monitoring tasks and acting as an additional safety net. It also improves interoperability among various systems through advanced data handling, a natural outcome of employing knowledge graphs for data management. Finally, the solution contributes to increasing sector capacity by automating certain monitoring tasks and facilitating the integration of other automation systems, thereby streamlining operations in air traffic control.