Establishing the Correlation Between Complexity and Performance for Arrival Operations

Abstract

Air traffic complexity indicators play an essential role in measuring operational performance and controller workload. However, current studies mainly depend on the manual scoring method to scale performance or workload. This paper focuses on arrival operations and presents a data-driven strategy to establish the correlation between complexity and performance to avoid the subjectivity of the currently used manual scoring method. Firstly, we present twenty-six indicators for describing air traffic complexity and two indicators for arrival operational performance. Secondly, the clustering method distinguishes peak and off-peak situations for arrival operation. Moreover, clustering results are compared to investigate the correlation between complexity and performance initially. Thirdly, the classification method is adopted to determine such correlation further. In addition, we also identify the affecting factors which could influence operational performance. Finally, trajectories of arrival aircraft landing at Guangzhou Baiyun International Airport (ZGGG) are used for case validation. The results indicate that there is a strong correlation between complexity and performance. The accuracy and precision of classification are approximately 90%. Furthermore, the number of aircraft significantly impacts the arrival operational performance within TMA.

Air Traffic Scenario Evaluation Based on Metric Learning

“…Due to the requirement of an extensive amount of labelled samples for training, supervised models face challenges when actual labelled samples are scarce and manual calibration is expensive. To address this, Zhu [9], Cao et al [10], Zhang [11] and Zhang et al [12] put forth alternative approaches for assessing airspace complexity, utilising techniques such as semi-supervised learning, transfer learning and unsupervised clustering. Zhu proposed a semi-supervised learning model capable of training with unlabelled samples.…”