Selection and Evaluation of Air Traffic Complexity Metrics

This paper presents an original method to evaluate air traffic complexity metrics. In previous works, we applied a Principal Component Analysis (PCA) to find the correlations among a set of 27 complexity indicators found in the literature. Neural networks were then used to find a relationship between the components and the actual airspace sector confiurations. Assuming that the decisions to group or split sectors are somewhat related to the controllers workload, this method allowed us to identify which components were significantly related to the actual workload. We now focus on the subset of complexity indicators issued from these components, and use neural networks to find a simple relationship between these indicators and the sector status.