Rapid urbanization has significantly exacerbated the Urban Heat Island (UHI) effect in high-density megacities, driven by the intensifying competition between built-up morphology and natural cooling infrastructure. Current research, however, often fails to accurately predict land surface temperatures (LST) because traditional models frequently overlook the complex spatial dependencies and neighborhood spillover effects inherent in urban environments. Existing studies often ignore the spatial dependence of heat transfer. This study proposes an explainable machine learning framework incorporating spatial lag variables to capture the thermal spillover from adjacent neighborhood context—such as green space cooling diffusion or built-up heat accumulation—which is frequently treated as noise in traditional models. Taking Shenzhen as a case study, we integrated multi-source data (Landsat 8, building vectors, DEM) and developed an XGBoost regression model (R² = 0.806) augmented with SHAP (Shapley Additive exPlanations) to quantify the contributions of local and contextual features. The results revealed that: (1) Non-linear Thresholds: Vegetation cooling exhibits a saturation effect, with the highest marginal benefit observed in the NDVI range of 0.2–0.4, while building warming effects converge at extremely high densities due to mutual shading; (2) Neighborhood Spillovers: Spatial interaction analysis confirms significant cool island synergy (where clustered green spaces provide amplified cooling) and heat island agglomeration effects—e.g., green spaces surrounded by high ecological backgrounds provide amplified cooling benefits; (3) Spatial Antagonism: A novel Interaction Balance Index (IBI) based on game-theoretic SHAP contributions was constructed to map the source-sink competition patterns, identifying distinct heat-dominated (West) and cool-dominated (East) zones. Unlike traditional area-weighted source-sink landscape metrics, IBI enables a pixel-level additive decomposition of warming and cooling factors, quantifying the net thermal outcome of local morphology and neighborhood spillover. By explicitly encoding spatial context into non-linear modeling, this study provides a more mechanistically robust understanding of urban thermal environments. The identified thresholds and dominant driver maps offer precise, spatially differentiated guidance for urban climate-adaptive planning and ecological restoration.

The building sector is a major source of global carbon emissions, with embodied carbon playing an increasingly critical role. This study quantitatively compares the life-cycle embodied carbon of three residential building design patterns (cast-in situ, CIS; design for disassembly, DfD; and skeleton–infill, SI) under a unified scenario of a 90-year service life with functional renovations every 30 years. A total of 36 cases, derived from twelve prototypical residential designs implemented in each pattern, were evaluated via life-cycle assessment following the EN 15978 standard. The results show that the SI pattern reduces embodied carbon by 45–55% compared to CIS, while the DfD pattern achieves a 35–45% reduction (with SI pattern consistently performing best). Structural system selection also influences outcomes, with shear wall structures reducing emissions by 7–14% compared to frame systems. Plan layout effects were marginal. The analysis indicates that the design pattern is the dominant factor influencing embodied carbon outcomes. SI pattern yields the largest carbon reduction by pairing a long-lived structural frame with flexible infill that extends service life and adaptability, while DfD lowers material demand via component reuse. These findings highlight the substantial benefits of circular design strategies and support a shift toward more adaptable, long-lifespan, and low-carbon residential design.

Accurately quantifying the driving mechanisms of land surface temperature (LST) is fundamental to developing climate-resilient urban strategies. However, traditional linear models often fail to capture the complex nonlinear interactions and spatial non-stationarity inherent in urban thermal environments, especially when hindered by multicollinearity among morphological indicators. This study proposes a multi-scale spatial explainability attribution framework by integrating an XGBoost machine learning model with SHAP (SHapley Additive Explanations) to decipher the thermal dynamics of Changchun, a representative cold-region city in China. Utilizing a 500 m grid-based dataset, we incorporated 3D urban morphology (BVD), land cover (NDVI, NDWI), and socioeconomic factors. The results indicate that the XGBoost model achieves superior predictive performance (R² = 0.694) compared to traditional OLS models. SHAP global attribution identified Building Volume Density (BVD) as the primary warming driver, as its three-dimensional volume creates “thermal traps” through radiation trapping and reduced ventilation. Notably, NDVI exhibits a significant nonlinear “cooling threshold effect” at 0.3, beyond which its mitigation efficiency stagnates or even reverses due to vegetation fragmentation and heat-induced physiological stress. Furthermore, spatial mapping reveals a distinct “sign reversal” in NDWI’s impact, reflecting the dualistic thermal regulation of water bodies across different urban–rural gradients. These findings suggest that urban thermal management strategies should shift from merely restricting 2D surface occupancy (e.g., Building Density) to a more sophisticated approach focused on precisely controlling 3D volume intensity (BVD). This study provides a “point-to-area” diagnostic tool supporting a transition to spatially targeted urban planning interventions.

The aim of this study is to identify, through layout-coverage testing, the upper fixed-wall ratio at which the reconfigurable layout set can still fully satisfy mainstream spatial demand, and to quantify, under consistent structural, temporal, and accounting conditions, how 90-year cumulative embodied carbon emissions change across δ scenarios and how crossing this threshold alters the residential update pathway. A design-sample database of 954 residential floor plans was used to develop a common “basic unit,” and a wall-based index, δ, was defined as the ratio of fixed-wall length to total interior-wall length. A multiple-response survey of 168 households was then used to establish a mainstream layout set; layouts were ranked by selection frequency, and the smallest ranked set whose cumulative share exceeded 50% of all selections was retained. Eleven δ scenarios were assessed over a potential 90-year service-life scenario that incorporated interior reconfiguration, I-wall renewal, and possible demolition–reconstruction. The results identify δ ≈ 0.72 as the upper fixed-wall-ratio threshold compatible with full coverage of the mainstream layout set. When δ ≤ 0.72, internal reconfiguration maintains mainstream-layout coverage, and cumulative embodied carbon ranges from 224.88 to 313.46 tCO₂e, equivalent to 1772.10–2470.13 kgCO₂e/m². When δ > 0.72, at least one mainstream layout becomes infeasible and the modeled update pathway shifts to demolition–reconstruction, increasing emissions to 402.62–503.95 tCO₂e, or 3172.73–3971.24 kgCO₂e/m². Dynamic trajectories for the representative δ = 0.72 and δ = 0.81 scenarios show that the former accumulates emissions gradually, with limited increases associated with I-wall renewal at Years 30 and 60, whereas the latter undergoes sharp jumps at the same nodes because insufficient layout coverage triggers demolition–reconstruction. These findings provide an operational basis for using the fixed-wall ratio as an early-stage carbon-screening variable while retaining the need for project-specific multi-performance verification.