Quantifying the impact of building material stock and green infrastructure on urban heat island intensity

The urban heat island (UHI) effect has become one of the most critical environmental consequences of urbanization, fundamentally linked to the accumulation of building material stocks and modification of natural surfaces. This study develops a comprehensive quantitative framework to analyze the combined effects of building material stock and green infrastructure on UHI intensity in Beijing, China. Using remote sensing data and interpretable machine learning approaches, particularly partial dependence analysis, we reveal the nonlinear relationships and interaction effects between urban physical characteristics and UHI intensity. The results identify a critical threshold of brick material stock at approximately 3 × 1 0 8 tons, beyond which UHI intensity increases sharply. Our findings advance the understanding of urban thermal environment regulation by quantifying both the individual and interactive effects of material stocks and green infrastructure, providing insights for optimizing urban heat mitigation strategies. • Machine learning reveals strong nonlinear relationships in urban heat island formation mechanisms. • Quantify critical thresholds in building material stock impacts on urban heat island intensity. • Demonstrated that spatial configuration of green infrastructure significantly influences its cooling efficacy. • Developed interpretable machine learning framework to analyze UHI formation mechanisms. • Scenario analysis shows 20% increase in green coverage can reduce UHI intensity by up to 0.46°C.