Decoding green space supply-demand mismatch through urban morphology: Toward equitable urban planning with...

Area of Science:

• Urban planning and spatial analysis
• Environmental justice and public health
• Geographic Information Systems (GIS) and machine learning

Background:

• Urban green spaces (UGS) are crucial for urban ecological infrastructure, resident well-being, and spatial equity.
• Rapid urbanization causes supply-demand imbalances and "green inequities" in UGS distribution.
• Understanding the spatial drivers of these mismatches is essential for equitable planning.

Purpose of the Study:

• To quantify UGS supply, demand, and spatial mismatches in Nanjing's central urban area in 2022.
• To reveal inequities in green resource allocation and accessibility.
• To identify urban morphological drivers influencing UGS supply-demand mismatches using machine learning.

Main Methods:

• Developed a framework to quantify UGS supply, demand, and spatial mismatches.
• Applied an explainable machine learning model (XGBoost-SHAP) to identify drivers.
• Analyzed data for traffic analysis zones (TAZs) in Nanjing's central urban area.

Main Results:

• Significant spatial mismatches were found across all TAZs, with core areas facing deficits and peripheral areas showing surpluses.
• "Quantitative abundance" of UGS did not guarantee "qualitative accessibility" for residents.
• Urban compactness, floor area ratio, road density, and land-use mix negatively impacted UGS supply-demand balance, while public facility coverage and residential land proportion had positive effects.

Conclusions:

• UGS planning must address spatial mismatches and "green inequities" beyond simple area provision.
• Urban morphology significantly influences the effectiveness and equity of UGS distribution.
• Governance strategies should prioritize urban morphology optimization for equitable green space services and environmental justice.