ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Download
Share
Publications Copernicus
Download
Citation
Share
Articles | Volume XII-4/W1-2026
https://doi.org/10.5194/isprs-annals-XII-4-W1-2026-343-2026
https://doi.org/10.5194/isprs-annals-XII-4-W1-2026-343-2026
28 Sep 2026
 | 28 Sep 2026

Spatially Constrained Clustering Framework for Urban Heat Risk Zone Identification

Agata Zabuska, Lidia Lazarova Vitanova, Tereza Trendafilova, and Dessislava Petrova-Antonova

Keywords: Machine Learning, Spatial Constrained Clustering, Geo Spatial Analysis, Weather Research and Forecasting Model, Wet Bulb Globe Temperature

Abstract. This study developed a spatially constrained clustering (SCC) framework for identifying urban heat-risk zones by integrating environmental heat hazard, population exposure, socio-demographic vulnerability, and mitigation indicators. Heat risk was conceptualized as a multidimensional framework, and SCC was applied to derive geographically contiguous zones in Sofia, Bulgaria. The results revealed a dominant urban–peripheral gradient in heat risk, with the urban core characterized by the co-occurrence of elevated thermal stress, high population density, and reduced mitigation capacity. While the SCC approach successfully identified spatially coherent and interpretable risk zones, the findings also suggest that additional variables and higher-resolution data are required to capture more detailed intra-urban differences. Overall, the proposed framework demonstrates the potential of integrating multidimensional geospatial data with the SCC approach to support urban heat-risk assessment and inform climate adaptation strategies.

Share