Dynamic Hot Spot Prediction by Learning Spatial- Temporal Utilization of Taxiway Intersections

Airports across the world are expanding by building multiple ground control towers and resorting to complex taxiway and runway system, in response to growing air traffic. Current outcome- based ground safety management at the airside may impede our potential to learn from and adapt to evolving air traffic scenarios, owing to the sparsity of accidents when compared with number of daily airside operations. To augment airside ground safety at Singapore Changi airport, in this study, we predict dynamic hot spots- areas where multiple aircraft may come in close vicinity on taxiways, as pre-cursor events to airside conflicts. We use airside infrastructure and A-SMGCS operations data of Changi airport to model aircraft arrival at different taxiway intersections both in temporal and spatial dimensions. The statistically learnt spatial-temporal model is then used to compute conflict probability at identified intersections, in order to evaluate conflict coefficients or hotness values of hot spots. These hot spots are then visually displayed on the aerodrome diagram for heightened attention of ground ATCOs. In the Subjective opinion of Ground Movement Air Traffic Controller, highlighted Hot Spots make sense and leads to better understanding of taxiway movements and increased situational awareness. Future research shall incorporate detailed human-in-the-loop validation of the dynamic hot spot model by ATCOs in 360 degree tower simulator.