Optimizing urban green space spatial patterns for thermal environment improvement: A multi-objective approach in the context of urban renewal

The rapid and inevitable trend of urbanization has amplified urban thermal challenges, intensifying the urban heat island (UHI) effect. Given the constraints of limited urban land resources, optimizing the spatial patterns of urban green space (UGS) to maximize their cooling potential is essential for mitigating urban thermal environments and supporting effective urban renewal planning. This research integrates the XGBoost model with the NSGA-II algorithm to propose a multi-objective approach to optimize UGS spatial patterns for thermal environment improvement, using the central urban area of Guangzhou, China, as a case study in the context of urban renewal. To further assess the effectiveness of optimization, the Shapley additive explanation (SHAP) model was employed to examine how landscape pattern metrics, which characterize UGS spatial patterns, influence LST before and after optimization. The results demonstrate that optimized UGS spatial patterns, achieved through a controlled expansion of UGS area, significantly alleviated thermal stress by reducing the total LST by 2,799.82 °C and lowering its standard deviation by 0.04. Industrial zones, densely populated areas, and commercial districts exhibited the most pronounced LST reductions that spatially corresponded to changes in UGS spatial patterns. In addition, post-optimization analysis revealed notable changes in key landscape pattern metrics: patch cohesion index (COHESION), patch density (PD), landscape shape index (LSI), and percent of landscape (PLAND). Compared to pre-optimization conditions, their positive contributions to LST were weakened, while their cooling effects were enhanced. This research provides a “space-for-time” planning paradigm that offers intuitive and actionable decision-making support for urban renewal planners and policymakers.