The European Air Traffic Management system is among the most complex systems in the world. Due to the dense nature of the European network, consequences of disruptions are often catastrophic. In particular, disruptions altering the expected flying time tend to pose great challenges to the arrival management of busy hubs. In response, EUROCONTROL released the Target Time Management (TTM) system, allowing airlines to issue Target Times of Arrival (TTA) even before depart. The TTM system helps hubs airports coordinate arrivals and departures. From the point of view of airlines, the advantage resides in being able to prioritize early arrivals of critical flights. Nevertheless, real-time prioritization is not trivial. Many studies have focused on this problem but with results limited to slot swapping in a tactical context. This is less effective compared to airlines having the ability to select a new slot at the pre-tactical level. This work covers this gap, allowing airlines to select the desired TTA even before departure. We use Deep Reinforcement Learning to create a dynamic arrival allocation model capable of prioritizing flights in terms of passenger connecting time, curfew performance, rotation delay, and fairness to other airlines. Additionally, the model is capable of adapting and react to the uncertainty in responses from the TTM. In the real-world, large anticipations in TTAs are often rejected. The model is tested with real data from SWISS International Airline. Results show an improvement of 5.9 minutes for critical passenger connection and 4.8 minutes for rotation delay versus a deterministic approach.

The capacity of the current system of air traffic is rapidly reaching a limit with the increasing demand for air transportation. Expected future traffic densities not only make automated conflict detection and resolution a necessity, but also force a re-evaluation of coordination elements to decrease conflict rate and severity. It has been acknowledged that airspace structure plays a positive role by acting as a first layer of conflict protection, reducing the likelihood of aircraft meeting and, consequently, the likelihood of conflicts and losses of minimum separation. In the recent past, different airspace structures have been explored. Research shows that the layered airspace concept, where groups of aircraft with similar headings remain separated by cruising at different altitudes, increases airspace capacity. However, implementation of this concept often employs an evenly distributed heading range per vertical layer, which is not optimal for all traffic scenarios, since it may lead to unevenly distributed numbers of aircraft per layer. In this work, we use supervised learning to determine a heading range distribution per layer adapted to the current traffic. This method resulted in a reduction of both conflicts and losses of minimum separation when compared to an evenly distributed layers concept. Results show that conflicts prevention, with a structure which efficiently segments aircraft through the airspace, may have a greater impact on safety than applying conflict resolution methods.