Abstract

As intensifying climate change and urban heat island (UHI) effects exacerbate outdoor thermal stress, residential neighborhoods increasingly face severe public health and cooling energy burdens. Conventional greening initiatives frequently rely on static, aesthetic-driven layouts that fail to account for complex microclimatic heat flows, localized solar geometry, and species-specific functional traits. To address these limitations, this study introduces an artificial intelligence (AI)-driven framework designed to optimize both the spatial placement and species selection of trees within residential yards for maximum heat mitigation. The proposed framework integrates high-resolution spatial data and machine learning models with human-centric thermal metrics—such as the Universal Thermal Climate Index (UTCI)—to evaluate temperature reductions at a micro-parcel scale. The findings provide actionable, data-driven design strategies that transcend generalized greening guidelines, offering homeowners and urban planners precise configurations to substantially lower localized ambient temperatures and enhance climate resilience.