The Context-Dependent Influence of Eye-Level Motor Traffic on Metro-Integrated Cycling: An AIGC-Enhanced Analysis

This study examines the context-dependent association between eye-level motor traffic and metro-integrated cycling in Shenzhen, China. To address the limitations of static street-view imagery, we constructed a traffic-informed AIGC-enhanced analytical framework to approximate peak-hour visual motor-traffic conditions. The resulting eye-level motor-traffic measure was incorporated into OLS, GWR, and MGWR models together with land-use, road-network, development-intensity, and streetscape variables. The results show that this measure was positively associated with metro-integrated cycling volume primarily during the weekday morning peak, while the association weakened or became statistically insignificant during evening and weekend periods. We describe this pattern as a commuter’s paradox-like association: visible motor traffic may co-occur with high first-/last-mile cycling demand in high-intensity commuting environments, rather than necessarily deterring cycling. The analysis further suggests a threshold-like land-use pattern in which residential density may act as a background precondition rather than a linear driver during peak hours. This study illustrates the methodological applicability of Geospatial Artificial Intelligence (GeoAI) for addressing static-data limitations and provides planning implications for evaluating station-area feeder cycling environments.