The improvement of the urban microclimate in the densely-built central areas of Mediterranean cities should be a key objective of integrated urban and transport planning and design in accordance with the UN Sustainable Development Goals on energy, sustainable cities, and climate action. The urban climate of cities in warm regions, already burdened by the urban heat island effect, is expected to worsen further due to the global climate crisis. This study investigates the performance of common environmental street design strategies on microclimate, thermal comfort, and air quality under extreme heat conditions in the Mediterranean city of Thessaloniki, Greece. A typology of streets was selected using criteria such as road functional classification and orientation, land uses, building height/street width ratio, the sky view factor, and the continuity/discontinuity of buildings. A conservative scenario (use of cool/photocatalytic and porous materials for sidewalks, lighter pavements, additional tree planting, installations of green roofs) and a radical scenario (pedestrianization and total traffic prohibition) of environmental design interventions were simulated using the ENVI-met 5.1 software. The research findings demonstrated that the car-free interventions combined with the use of environmentally friendly materials in the public realm could significantly reduce the heat island effect and mitigate gaseous pollutants. The perceived air temperature (Physiological Equivalent Temperature—PET index) can decrease by up to 15 °C in well-shaded locations and near building corners, while nitrogen oxides can be reduced by up to 87% when considering a more radical pedestrianization scenario. The standardization of environmental interventions following a typology of urban streets could support planners and decision-makers in detecting the appropriate solutions for improving the urban microclimate.

Advances in Machine learning open new frontiers in the systematic analysis of urban form. The study presents a scalable and interpretable framework that derives an urban-form typology by performing unsupervised clustering of 17 multi-scale morphological indicators encoded at the cadastral plot scale. The method adds positional information with the Getis-Ord Gi* spatial autocorrelation metric to encourage spatially homogeneous clusters. The study employs a combination of UMAP for non-linear dimensionality reduction and BIRCH for scalable clustering. Caveats of using the plot as a spatial unit are mitigated via filtering, tessellation and buffering. Applied to the metropolitan area of Thessaloniki, Greece, the framework identifies 14 urban form types organized into five families with similar characteristics. The resulting typology reveals, in a Conzenian fashion, patterns of urban development rooted in the city’s modern history. Results are validated quantitatively with performance metrics and qualitatively using aerial imagery and established knowledge of Thessaloniki’s planning and evolution.