Scalability of Set-based Air Traffic Forecasting
Background: Air traffic flow prediction is evolving from traditional macroscopic time-series forecasting toward models that treat the airspace as a dynamic set of microscopic aircraft states. Evaluating the scalability and long-term viability of set-based representations in large-scale, high-density environments remains an open research challenge.
Question / Future Work: There is a need to quantify how set-based state representations scale with increasing air traffic density and whether they maintain performance across diverse, heterogeneous airspace structures, particularly in closed-loop control environments.
Why It Matters: As a paradigm shift, validating the robust scaling of these set-based architectures is essential to determine if they can replace legacy time-series methods in operational settings.
Metadata & Links
- created_at
- 2026-04-16T05:46:46Z