Patterns of spatially refined urban built environment stocks across Chinese cities

We developed an approach combining big data mining technology, bottom-up stock modeling and Chinese temperature-zone MCI database to calculate and predict the urban built environment stocks in 2020. We considered building, road, railway and metro, and aimed to characterize their quality, composition, and spatial distribution. By applying this approach to 50 cities, we found considerable diversities MS quality, composition and distribution, discussed the impact factors and growth patterns among cities, and highlighted the disparities behind economic conditions, population size, built-up area, development rate, land use, geographical location, and urban form.本研究构建了一套融合大数据挖掘技术、自下而上存量建模方法与中国温度带MCI数据库的研究框架，用于测算并预测2020年的城市建成环境存量。本研究覆盖建筑、道路、铁路与地铁四类对象，旨在表征其质量、构成与空间分布特征。通过将该框架应用于50座城市，我们发现不同城市在质量、构成与空间分布上存在显著差异；同时探讨了城市间的影响因素与增长模式，并揭示了经济水平、人口规模、建成区面积、发展速率、土地利用、地理位置与城市形态等维度背后的发展差距。