
Vitality transfer patterns are essential for creating vibrant, sustainable cities, yet their dynamic changes over time remain underexplored. Taking Nanjing as a case study, this study employed 24 h of location-based service data as a time series to explore the vitality transfer pattern within a day from both distribution and aggregation perspectives. Spatial dependence decay patterns were detected using residual clustering relationships, and the LightGBM model was used to explore the relationship between vitality transfer and 50 factors in five categories: transportation, function, economy, morphology, and geography. The results show that the urban vitality distribution has a polycentric agglomeration pattern, which goes through four periods in a day. Vitality transfer is the cyclical process of transformation from one aggregated state to another. The spatial dependence was maximized at 0.75 km2. The magnitude of vitality fluctuation is strongly influenced by factors such as morphology, transportation, and function. Spatial differences in factors combine to drive vitality transfer in distribution and aggregation, with factors such as accessibility and building age diversity influencing distribution, and factors such as accessibility and POI diversity altering aggregation. This study supports the rational design of vibrant urban spaces and promotes effective vitality transfer and sustainable urban development.
Big data, Sustainability, Nanjing, Urban vitality transfer, Machine learning, Architecture, Spatial effects decay laws, NA1-9428
Big data, Sustainability, Nanjing, Urban vitality transfer, Machine learning, Architecture, Spatial effects decay laws, NA1-9428
| selected citations These citations are derived from selected sources. This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically). | 0 | |
| popularity This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network. | Average | |
| influence This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically). | Average | |
| impulse This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network. | Average |
