Data-driven recognition of hot taxiway segments for assessing airport surface traffic efficiency

Abstract

Due to the continuous growth in air transportation demand, the complexity of airport surface traffic systems, and the variability in aircraft behavior, airport surface traffic exhibits serious spatial heterogeneity. This complexity not only heightens the likelihood of surface conflicts and unsafe events, but also has a substantial impact on both the operational efficiency and safety of airport operations. Current research on airport surface hotspots mainly focuses on conflict hotspots and risk hotspots, and fewer studies are conducted on busy hotspots. In order to fill this research gap, this paper proposes an accurate matching method of airport surface trajectory and taxiway system based on Hidden Markov Algorithm. And establishes an indicator system to characterize airport surface taxiway, which is used to comprehensively reflect the airport surface taxiway operation efficiency. On this basis, an Airport Surface Hot-Taxiway-Segment Recognition Model (ASHRM) is proposed which innovatively introduces the new concept of hot index to quantify and measure the popularity of taxiway segments, thus realizing the recognition of hot taxiway segments. Through the experimental analysis of real data from SZX Airport, the results show that the recognized hot taxiway segments are consistent with actual airport operations, and the cumulative traffic flow is identified as the most critical factor affecting the formation of hot taxiway segments. This method not only provides a scientific basis for the operational management and efficiency assessment of airports, but also realizes the scientific recognition of hot taxiway segments in the dynamically changing airport surface transportation systems.