China's rapid urbanization presents significant challenges for rural construction and resource management, often prioritizing economic gains over climate adaptability and energy efficiency. This study focuses on traditional Huizhou houses, integrating energy consumption and comfort analysis into the early design stages. Initial simulations using the Universal Thermal Climate Index (UTCI) established a baseline model for comparison. Through the Wallacei_X plugin, optimized designs achieved a 19.88% reduction in energy use intensity (EUI) and a 9.37% improvement in summer outdoor comfort (UTCI_H) compared to the baseline. Further analysis along the Pareto frontier using Scikit-learn demonstrated high predictive accuracy with XGBoost (F1 scores: 0.80 for 4-side houses, 0.78 for 3-side houses). To enhance interpretability, SHapley Additive exPlanations (SHAP) analysis explored nonlinear relationships between design variables and building performance, while coupling analysis examined the spatial relationships between houses and their environmental impact. In the final validation, the proposed workflow effectively linked building performance prediction with design optimization, achieving a 26% performance improvement over the original site plan. This integrated approach enables rapid performance evaluations, reduces costs, and provides practical design references. It highlights the potential of combining genetic algorithms and machine learning to drive sustainable rural development.
扫码关注我们
求助内容:
应助结果提醒方式:
