Abstract: Public EV charging stations (EVCSs) are essential for EV adoption. This study analyzes Seoul’s public EV charging patterns in relation to the urban built environment. Built-environment data were collected from land-use maps, POI data, and panorama images, with computer vision extracting scene features. A spatiotemporal analysis revealed peak afternoon usage, with additional late-evening peaks near mega-retail stores on weekdays. Public EVCSs were used more on weekdays, with central business districts experiencing the highest demand, sometimes nearing overuse. Cluster analysis identified unique built-environment patterns, with high-usage stations having more parking areas. Computer vision detected highways, parking lots, and crosswalks as common surroundings. Outlier analysis highlighted fast chargers in business districts. Findings suggest POI data and computer vision complement each other in assessing built environments, offering insights to optimize public EVCS usage.
