Urban block form significantly impacts energy and environmental performance. Therefore, optimizing urban block design in the early stages contributes to enhancing urban energy efficiency and environmental sustainability. However, widely used multi-objective optimization methods based on performance simulation face the challenges of high computational loads and low efficiency. This study introduces a framework using machine learning, especially the XGBoost model, to accelerate multi-objective optimization of energy-efficient urban block forms. A residential block in Nanjing serves as the case study. The framework commences with a parametric block form model driven by design variables, focusing on minimizing building energy consumption (EUI), maximizing photovoltaic energy generation (PVE) and outdoor sunlight hours (SH). Data generated through Latin Hypercube Sampling and performance simulations inform the model training. Through training and hyperparameter tuning, XGBoost’s predictive accuracy was validated against artificial neural network (ANN), support vector machine (SVM), and random forest (RF) models. Subsequently, XGBoost replaced traditional performance simulations, conducting multi-objective optimization via the NSGA-Ⅱ algorithm. Results showcase the framework’s significant acceleration of the optimization process, improving computational efficiency by over 420 times and producing 185 Pareto optimal solutions with improved performance metrics. SHAP analysis highlighted shape factor (SF), building density (BD), and building orientation (BO) as key morphological parameters influencing EUI, PVE, and SH. This study presents an efficient approach to energy-efficient urban block design, contributing valuable insights for sustainable urban development.

Urbanization has led to changes in urban morphology and climate, while urban open space has become an important ecological factor for evaluating the performance of urban development. This study presents an optimization approach using computational performance simulation. With a genetic algorithm using the Grasshopper tool, this study analyzed the layout and configuration of urban open space and its impact on the urban micro-climate under summer and winter conditions. The outdoor mean Universal Thermal Climate Index (UTCI) was applied as the performance indicator for evaluating the quality of the urban micro-climate. Two cases—one testbed and one real urban block in Nanjing, China—were used to validate the computer-aided simulation process. The optimization results in the testbed showed UTCI values varied from 36.5 to 37.3 °C in summer and from -4.9 to -1.9 °C in winter. In the case of the real urban block, optimization results show, for summer, although the average UTCI value increased by 0.6 °C, the average air velocity increased by 0.2 m/s; while in winter, the average UTCI value increased by 1.7 °C and the average air velocity decreased by 0.2 m/s. These results demonstrate that the proposed computer-aided optimization process can improve the thermal comfort conditions of open space in urban blocks. Finally, this study discusses strategies and guidelines for the layout design of urban open space to improve urban environment comfort.