One of the functions of air traffic management is to balance airspace capacity and air traffic demand. This balancing act starts well in advance of the day of operation but is generally based on flight plan data, weather forecasts, and so on. On the day of operation, the actual trajectory of an aircraft may differ significantly from its flight plan (due to convective weather, ground delays, airspace restrictions, etc.) and this may lead to demand-capacity imbalance, as well as 4D areas of high traffic complexity. Although measures are taken to address these issues on the day, areas of high traffic complexity still occur and these generally have to dealt with by air traffic controllers (ATCOs) without sufficient advance notice. 

SESAR researchers are developing a solution which will predict areas of high traffic complexity at least one hour before the concerned traffic enters the area of responsibility of a controller. In addition, the solution will suggest clearances that can be applied to resolve each area of high traffic complexity, such as requesting one or more aircraft to reroute, or to climb to a particular altitude. Care will be taken to ensure that these clearances do not to create conflicts and other areas of high traffic complexity elsewhere, and to minimise the number of clearances.

The candidate solution focuses on en-route traffic in busy airspace and exploits machine learning. The research includes developing and validating: an operational concept and operating procedures; an aircraft trajectory prediction tool; algorithms to predict and resolve areas of high traffic complexity; and a graphical human-machine interface to allow flow management position (FMP) personnel to interact with the solution. 

BENEFITS

The candidate solution is expected to reduce controller workload; increase capacity and efficiency; and improve safety and environmental sustainability.