Optimizing eVTOL Time Scheduling through Origin-Destination and Temporal Data Analysis

This study introduces a novel data-driven methodology to optimize the scheduling and station placement of electric vertical take-off and landing (eVTOL) vehicles, addressing key challenges in urban air mobility (UAM). Using São Paulo's metropolitan area and New York City as case studies, the research integrates diverse datasets—including helicopter path data, heliports, Uber Movement data, taxi data, and Google API information—to analyze traffic patterns, origin-destination pairs, and peak usage times. The study identifies strategic locations for eVTOL stations and optimal flight schedules by employing clustering algorithms and proximity analysis. The primary contribution is a framework that generates a comprehensive dataset in .csv format, detailing routes and schedules tailored to urban mobility needs and supporting the planning and deployment of eVTOL operations. This scalable and adaptable approach enables integrating urban traffic data into eVTOL planning, advancing sustainable transportation systems, and enhancing the efficiency of UAM solutions worldwide.