Urban thermal environments, characterized by the interplay between indoor and outdoor conditions, pose growing challenges in high-density coastal cities. This study proposes a multi-scale, integrative framework that couples a satellite-derived land surface temperature (LST) analysis with microscale building performance simulations to holistically evaluate the high-density urban thermal environment in subtropical climates. The results reveal that compact, high-density morphologies reduce outdoor heat stress (UTCI) through self-shading but lead to significantly higher cooling loads, energy use intensity (EUI), and poorer daylight autonomy (DA) due to restricted ventilation and limited sky exposure. In contrast, more open, vegetation-rich forms improve ventilation and reduce indoor energy demand, yet exhibit higher UTCI values in exposed areas and increased lighting energy use in poorly oriented spaces. This study also proposes actionable design strategies, including optimal building spacing (≥15 m), façade orientation (30–60° offset from west), SVF regulation (0.4–0.6), and the integration of vertical greenery to balance solar access, ventilation, and shading. These findings offer evidence-based guidance for embedding morphological performance metrics into planning policies and building design codes. This work advances the integration of outdoor and indoor performance evaluation and supports climate-adaptive urban form design through quantitative, policy-relevant insights.

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.