EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Street Vitality–Low-Carbon Coordination: Spatial Heterogeneity and Nonlinear Mechanisms from Interpretable Machine Learning

Shukai Zhang, Chengzhi Yu, Shuang Liang

Sustainability · 10.06.2026 · 18 (12) · 5965

DOI: 10.3390/su18125965 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sustainability, online erschienen am 10.06.2026. Verfasst von Shukai Zhang und 2 weiteren Autor:innen. Die Arbeit nennt 55 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This study reframes street-level sustainable urban renewal as a coordination problem between street vitality and relative low-carbon performance, rather than treating vibrant activity and carbon-pressure reduction as separate planning objectives. Its main contribution is an integrated street-level diagnostic framework that combines multidimensional vitality measurement, township-constrained carbon-emission reference estimation, vitality–carbon mismatch identification, and interpretable nonlinear mechanism analysis within unified street analytical units. Although previous studies have substantially advanced the measurement of street vitality and urban carbon emissions, these two strands of research have often developed separately. As a result, limited evidence is available on whether high-vitality streets also perform well in low-carbon terms, where vitality–carbon mismatches emerge, and which built-environment conditions are associated with more coordinated outcomes. Taking the five central districts of Chengdu, China, as a case, this study integrates multi-source activity, mobility, built-environment, and emission-related data. Street vitality is measured through activity agglomeration, temporal continuity, functional support, and external connectivity, while relative low-carbon performance is derived from the reverse normalization of length-normalized carbon-emission intensity based on a township-constrained street-level emission reference estimate. The results show that street vitality and low-carbon performance are spatially uneven and frequently mismatched, as high activity does not automatically translate into stronger low-carbon performance, and lower-carbon pressure does not necessarily indicate a vibrant urban environment. More coordinated streets are associated with context-specific combinations of functional organization, transport operation, built form, street-interface quality, and ecological background. Nonlinear diagnostic results further suggest that coordination is favored by moderate, balanced, and locally adapted built-environment conditions rather than by the simple maximization of individual indicators. These findings shift the discussion from whether vitality and low-carbon performance are desirable in isolation to how they can be jointly diagnosed and improved in street-level urban renewal.

Zitieren

APA

Zhang, S., Yu, C., & Liang, S. (2026). Street Vitality–Low-Carbon Coordination: Spatial Heterogeneity and Nonlinear Mechanisms from Interpretable Machine Learning. Sustainability, 18(12), 5965. https://doi.org/10.3390/su18125965

Vancouver

Zhang S, Yu C, Liang S. Street Vitality–Low-Carbon Coordination: Spatial Heterogeneity and Nonlinear Mechanisms from Interpretable Machine Learning. Sustainability. 2026;18(12):5965. doi:10.3390/su18125965

BibTeX
@article{Zhang2026,
  author = {Zhang, Shukai and Yu, Chengzhi and Liang, Shuang},
  title = {Street Vitality–Low-Carbon Coordination: Spatial Heterogeneity and Nonlinear Mechanisms from Interpretable Machine Learning},
  journal = {Sustainability},
  year = {2026},
  volume = {18},
  number = {12},
  pages = {5965},
  doi = {10.3390/su18125965}
}
Kostenlos starten →