Reproduce “Graph-based Complexity Forecasts in UK En Route Airspace Using Relevant Aircraft Interactions” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Edward Henderson, George De Ath, Nick Pepper
The authors develop a sector-specific method to forecast pairs of aircraft that may require monitoring in London Middle Sector. It adapts an ATCO-informed relevance filter and combines uncertain route-arrival times with a probabilistic graph-based forecast. On one May 2025 day, 45-minute predictions correlated at 0.68 with filter-identified pair counts, versus 0.55 for aircraft-volume forecasts; this remains a workload proxy, not a direct measurement.
Key insights
- A refined, ATCO-validated "relevant aircraft pairs" filter offers a more accurate and nuanced proxy for ATCO workload than traditional traffic volume counts.
- A graph-based representation of airspace, combined with probabilistic modeling of aircraft movement and historical interaction data, effectively forecasts complex spatial-temporal interactions.
- Integrating real-time operational data, specifically last-issued ATCO instructions for trajectory predictions, enhances the realism and accuracy of complexity forecasts by accounting for deviations from filed flight plans.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.