Data-driven vertiport siting: A comparative analysis of clustering methods for Urban Air Mobility

Abstract

Urban Air Mobility (UAM) has emerged as a promising solution to enhance metropolitan urban mobility. A critical determinant of UAM’s success is vertiport siting, which directly influences accessibility and travel time benefits. However, existing research lacks a evaluation of different data-driven clustering approaches for vertiport placement. This study systematically compares six clustering-based vertiport allocation strategies against an expert-defined benchmark (OBUAM) in the Munich Metropolitan Region (Ploetner et al., 2020). More specifically, the travel time efficiency improvements, accessibility enhancements, and transport equity impacts are assessed across different allocation scenarios. Results indicate that clustering-based siting significantly outperforms expert-defined siting in all the three perspectives. Notably, the K-means++ approach achieves the highest travel time saving (10.05%), accessibility gains (7.16%) and the lowest Gini coefficient (0.512), demonstrating its advantages in planing vertiport locations. The inferiority of DBSCAN, OBUAM and MS scenarios reveals that neither concentrating vertiports excessively in urban centers nor distributing them too evenly across the region optimizes transport efficiency. All clustering-based methods offer a practical, data-driven alternative that does not rely on domain expertise or excessive computational resources, making them easily adaptable for real-world UAM planning. Sensitivity analyses further explore the influence of key parameters on the indicators. Findings highlight that reducing pre-flight time has a more significant impact on travel time saving, accessibility and equity than increasing UAM cruise speed, while higher fares significantly disproportionately reduce accessibility benefits and equality.