City Fly: Modeling demand and vertiport location jointly for urban commuting

• A joint model links demand forecasting with vertiport site optimization. • Socioeconomic indicators are used to estimate air mobility commuting demand. • Optimization considers noise exposure, operational cost, and demand coverage. • The model enhances adaptability and generalization in complex urban settings. • A Chengdu-based case study demonstrates the method’s real-world effectiveness. The rapid development of electric vertical take-off and landing (eVTOL) aircraft presents transformative opportunities for urban air mobility (UAM). As cities globally accelerate infrastructure development, vertiport placement must reconcile demand-driven accessibility with geographic feasibility to address societal needs. However, only a limited number of studies have embedded precise demand analysis into vertiport location selection models, and empirical research using real-world data remains underexplored. This paper proposes a novel three-step demand forecasting and multi-objective optimization model (3DF-MOM) that jointly addresses these challenges. The model predicts UAM commuting demand with minimal prior knowledge, utilizing urban geographic information system (GIS) layers to optimize vertiport location selection under dual societal-geographic criteria: minimizing noise exposure for densely populated neighborhoods, lowering operational expenditures through cost-effective spatial configuration, and maximizing demand coverage across spatially fragmented urban zones. An empirical study was conducted based on urban geographic information data from Chengdu, China, in combination with ArcGIS. The results show that there will be 155 eVTOL aircraft commuting trips per day in Chengdu by 2030. The model optimally balances noise control, efficiency, and demand coverage with six vertiports of different sizes. The 3DF-MOM framework advances sustainable low-altitude infrastructure development by embedding geographic intelligence and social equity metrics into decision-making, offering policymakers a scalable tool to harmonize environmental, economic, and spatially inclusive service quality objectives.