Search papers, labs, and topics across Lattice.
This study investigates the feasibility of using radar imagery as input for deep learning vision models to estimate air traffic complexity, a task traditionally performed by human controllers. By encoding traffic situations into position images with additional aircraft state variables and employing a Vision Transformer (ViT), the model successfully regresses four complexity components with an R虏 value exceeding 0.96. Notably, the model's sensitivity to aircraft removal reflects its ability to capture operationally significant variations in sector complexity, indicating that radar imagery can effectively inform air traffic management systems.
Radar imagery can outperform traditional methods in estimating air traffic complexity, achieving over 96% accuracy in modeling critical operational metrics.
Air traffic controllers perceive traffic complexity through the radar display, suggesting that a computer vision model operating on the same imagery may provide a natural architecture for modeling controller-perceived complexity; however, whether radar imagery is a viable input format for deep learning vision models remains unclear. Unlike natural images, radar images are extremely sparse and self-similar, consisting primarily of a black background and a few visually identical aircraft blobs, while small changes in aircraft positions can substantially alter sector-level complexity. To test whether a vision model can capture these operationally important differences, we encode each traffic situation as a position image supplemented by five channels representing aircraft state variables, including heading, speed, and altitude, and train a Vision Transformer (ViT) to regress four intrinsic complexity components derived from pairwise geometric relations among aircraft. The model achieves $R^2>0.96$ for all four components, and a one-aircraft-removal perturbation study shows that its response changes proportionally to how much the removed aircraft contributed to sector complexity rather than treating every removal as equivalent. These results demonstrate that, despite its atypical visual characteristics, radar imagery is a viable input format for air traffic complexity modeling.
