Feng Yuting, Huang Shaoyu, Chen Shengze, Guan Chenghe, Li Ying, Tan Qiaoyu, Jin Yaohui, Yang Xiaokang, Xu Yanyan
MoE Key Laboratory of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, 200240, China.
Data-Driven Management Decision Making Lab, Shanghai Jiao Tong University, Shanghai, 200240, China.
Sci Data. 2025 Jul 18;12(1):1260. doi: 10.1038/s41597-025-05581-w.
Research on urban green spaces remains active, with a shift towards data-driven methodologies. Leveraging mobile phone data from 10 million anonymized users in Shanghai, we identify park visitations over four months and construct a real population-level daily dynamic mobility network (GreenMove) that reveals how different residential polygons and parks are connected. The edges are weighted with informative metrics, including flow, commuter ratio, and distance between nodes. It bridges the "demand-supply" gap by modeling polygon-park connections and quantifies park demand and attractiveness. Beyond considering the geographic characteristics of parks and their competitive interactions, we associate comprehensive and consistent socioeconomic indicators with the network, as well as granular weather data. GreenMove serves as a dynamic topology that demonstrates the pattern of residents' enjoyment of green spaces and offers multi-dimensional insights to urban park research advancement and equity-focused planning. It particularly offers a critical temporal benchmark for understanding the longitudinal evolution of cities and vertical dynamics in how human access to parks, as well as facilitating broader fields of future sustainable city design.
关于城市绿地的研究依然活跃，且正朝着数据驱动的方法转变。利用来自上海1000万匿名用户的手机数据，我们确定了四个月内的公园访问情况，并构建了一个真实的人口层面的每日动态移动网络（GreenMove），该网络揭示了不同居住区域与公园是如何连接的。边由包括流量、通勤率和节点间距离等信息指标加权。它通过对区域与公园的连接进行建模弥合了“供需”差距，并量化了公园需求和吸引力。除了考虑公园的地理特征及其竞争互动外，我们还将全面且一致的社会经济指标以及详细的天气数据与该网络相关联。GreenMove作为一种动态拓扑结构，展示了居民享受绿地的模式，并为城市公园研究进展和以公平为重点的规划提供了多维度见解。它尤其为理解城市的纵向演变以及人类进入公园的垂直动态提供了关键的时间基准，同时也促进了未来可持续城市设计的更广泛领域。
