Balancing Solar Energy, Thermal Comfort, and Emissions: A Data-Driven Urban Morphology Optimization Approach

Urban morphology critically shapes environmental performance, yet few studies integrate multiple sustainability targets within a unified modeling framework for its design optimization. This study proposes a data-driven, multi-scale approach that combines parametric simulation, artificial neural network-based multi-task learning (MTL), SHAP interpretability, and NSGA-II optimization to assess and optimize urban form across 18 districts in Hong Kong. Four key sustainability targets—photovoltaic generation (PVG), accumulated urban heat island intensity (AUHII), indoor overheating degree (IOD), and carbon emission intensity (CEI)—were jointly predicted using an artificial neural network-based MTL model. The prediction results outperform single-task models, achieving R² values of 0.710 (PVG), 0.559 (AUHII), 0.819 (IOD), and 0.405 (CEI), respectively. SHAP analysis identifies building height, density, and orientation as the most important design factors, revealing trade-offs between solar access, thermal stress, and emissions. Urban form design strategies are informed by the multi-objective optimization, with the optimal solution featuring a building height of 72.11 m, building centroid distance of 109.92 m, and east-facing orientation (183°). The optimal configuration yields the highest PVG (55.26 kWh/m²), lowest CEI (359.76 kg/m²/y), and relatively acceptable AUHII (294.13 °C·y) and IOD (92.74 °C·h). This study offers a balanced path toward carbon reduction, thermal resilience, and renewable energy utilization in compact cities for either new town planning or existing district renovation.