2022 data quantifying supply, demand, and spatial mismatches of urban green spaces (UGS) in the central urban area of Nanjing. The dataset was created by Lijuan Sun and uses an explainable machine learning model (XGBoost–SHAP) to identify urban morphological drivers of mismatches. It includes results for 251 traffic analysis zones (TAZs).
Use Cases
- Identifying areas with green space deficits or surpluses based on quantified supply-demand mismatches.
- Analyzing the impact of urban compactness and floor area ratio on green space balance.
- Investigating how road density and land-use mix amplify spatial inequities.
- Evaluating the role of public facility coverage and residential land proportion in mitigating mismatches.
- Developing governance strategies for equity-oriented green space planning in rapidly urbanizing regions.
Strengths
- Includes results for 251 traffic analysis zones (48 in deficit, 203 in surplus).
- Applies an explainable machine learning model (XGBoost–SHAP) to identify drivers.
- Focuses on a specific geographic case study (central urban area of Nanjing) for 2022.
Limitations
- Column-level documentation is absent; field semantics must be inferred after download.
- Row count is unknown, which may limit suitability assessment.
- The dataset is very small (5.5 KB), suggesting limited scope or aggregated summary data.
Provenance
- Source
- figshare
- Collection Method
- Likely derived from urban planning analysis and machine learning modeling.
- Time Range
- 2022
- Freshness
- Last updated 2026-03-18 17:24:45; freshness should be verified.
- Geography
- Central urban area of Nanjing, China.