Unsupervised clustering approach to residential typo-morphologies across multiple cities for urban heat vulnerability assessment

• GSI, FSI, OSR, H avg , and FVC refine typo-morphologies for LCZ residential types. • Our approach enhances existing and reveals new LCZ subclasses in the Dutch urban context. • Compact typo-morphologies (LCZ 2 and LCZ 42) exhibits highest UHI max intensities. • Most low-rise typo-morphologies have low tree coverage. • Typo-morphologies mapped on a 100 × 100 m grid cells support linking census data. Residential environments are central to addressing urban heat stress for vulnerable populations and are prime targets for implementing climate adaptation strategies. The reliance on urban heat island (UHI) intensity mapping alone has been argued to provide limited guidance for adaption efforts, whereas linking heat patterns to the built environment characteristics through frameworks such as Local Climate Zones (LCZ) provides more meaningful insights for developing neighborhood cooling strategies. However, widely used LCZ maps often misrepresent intra-type variation and cannot capture subclasses beyond the standardized framework. This paper presents an unsupervised clustering approach to identify residential typo-morphologies across 99 Dutch cities, enhancing their relevance for urban heat vulnerability assessments. The analysis reveals that five morphological parameters (FSI, GSI, OSR, H avg , and FVC) selected from 17 parameters are sufficient to identify nine distinct residential typo-morphologies relatable to LCZs within 100 × 100 m grid cells. The evaluations demonstrate that this approach detects underrepresented LCZ types and reveals new sub-classes absent from standard LCZ classifications. Key findings include detection of high-density areas (LCZ 4 2 ) reflecting recent urban densification with one of the highest UHI max next to LCZ 2 (4.2-4.9 K), and vegetation-differentiated variants within sparse and low-rise categories LCZ 9 D and LCZ 6 D , distinguished by distinctive UHI max (0.5-0.7 K higher) compared to their base types. Notably, tree coverage remains low across low-rise and compact typo-morphologies, revealing substantial opportunities for greening interventions. This data-driven refinement preserves LCZ's global comparability while considering local specificity, providing improved frameworks to inform targeted climate adaptation strategies in residential environments.