Abstract
In dense urban cores with limited land, the distribution of visible street greenery remains poorly understood. Using Shanghai’s Huangpu District, this study quantifies the Green View Index from 77,256 street-view images at 19,314 sampling points. An interpretable framework combining Random Forest with SHAP and optimal-parameter GeoDetector is applied to examine nonlinear and spatially interactive mechanisms shaping green inequality. Results show a mean GVI of only 12.7% with pronounced green inequality. Vegetation abundance and landscape configuration are the dominant drivers, with nonlinear thresholds and factor interactions jointly shaping visible greenery.
| Original language | English |
|---|---|
| Number of pages | 20 |
| Journal | Journal of Urban Design |
| DOIs | |
| Publication status | E-pub ahead of print - 9 Sept 2026 |
UN SDGs
This output contributes to the following UN Sustainable Development Goals (SDGs)
-
SDG 15 Life on Land
User-Defined Keywords
- Green view index
- landscape pattern
- machine learning
- street view
- urban greening
Fingerprint
Dive into the research topics of 'Understanding green inequality in dense urban cores: nonlinear and spatially interactive drivers of street-level greenness'. Together they form a unique fingerprint.Cite this
- APA
- Author
- BIBTEX
- Harvard
- Standard
- RIS
- Vancouver