Spatial patterns of residents’ daily activity space and its influencing factors based on the CatBoost model: A case study of Nanjing, China

Abstract

The complexity and fragmentation of people's activity space are challenging to planners. However, the relevant studies are mostly concerned on the relationship between the social attributes and the activity space of residents in a single or several communities, or the spatiotemporal laws of activity space on a macro scale. The research on the spatial characteristics of residents' activity space still needs to be strengthened. The present study analyses the spatial patterns of residents' activity space based on mobile phone signaling data to fill the gap of previous studies that assessed residents' activity space across small geographic areas. First, according to the spatial scope and direction of an activity space and residents' activity coverage rate, spatial patterns can be divided into three types: compact, extended, and directional extension patterns. The CatBoost method is then used to statistically analyze the influencing variables of spatial patterns, and the order of importance of the following influencing factors is determined: the built environment is more influential than social and economic situations. This study aims to strengthen the understanding of residents' activity space at the spatial level and provide a basis for the optimization of communities with different spatial patterns.