Unveiling the Spatial Heterogeneity of Urban Vitality Using Machine Learning Methods: A Case Study of Tianjin, China

Fengshuo Sun and Enxu Wang ()
Additional contact information
Fengshuo Sun: Jangho Architecture College, Northeastern University, Shenyang 110169, China
Enxu Wang: Jangho Architecture College, Northeastern University, Shenyang 110169, China

Land, 2025, vol. 14, issue 7, 1-25

Abstract: The impact of the built environment (BE) on urban vitality (UV) has become a key issue in the field of urban planning. However, few studies have explored the impact of the BE on UV from the perspective of urban function zones (UFZs). Taking the central urban area of Tianjin as an example, this paper explores the nonlinear influences and threshold effects of the BE on UV using machine learning methods. It also reveals the spatiotemporal variations in UV across different UFZs during the daytime and nighttime on weekdays and weekends. The results show the following: (1) Education and culture zones showed the highest UV during weekday daytime, while commercial zones dominated at other times. Industrial zones remained the least active throughout. Residential zones demonstrated higher nighttime UV than daytime UV on weekdays, with the opposite pattern observed on weekends. Public service zones maintained a comparable level of UV between the daytime and nighttime on weekdays. Other function zones generally displayed higher daytime UV. During the daytime on weekends, all function zones except industrial zones demonstrated higher UV compared to other time periods. (2) In commercial zones, the floor area ratio (FAR) exerted the strongest influence, displaying distinct threshold effects. Residential zones showed dual sensitivity to building height (BH) and the FAR. Public service zones were predominantly influenced by Road Density (RD) and Bus Station Density (BSD). RD exhibited higher marginal utility for enhancing UV during the nighttime. Education and culture zones were significantly influenced by the FAR, RD, and POI Density (POID).

Keywords: urban vitality; built environment; urban functional zones; nonlinear relationships; threshold effects; machine learning methods (search for similar items in EconPapers)
JEL-codes: Q15 Q2 Q24 Q28 Q5 R14 R52 (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/2073-445X/14/7/1316/pdf (application/pdf)
https://www.mdpi.com/2073-445X/14/7/1316/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jlands:v:14:y:2025:i:7:p:1316-:d:1683974

Access Statistics for this article

Land is currently edited by Ms. Carol Ma

More articles in Land from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().