Spatially-constrained clustering of geospatial features for heat vulnerability assessment of favelas in Rio de Janeiro

2026-04-30 · Source: cs.LG updates on arXiv.org · Field: Science & Research — Environmental Science & Earth Systems, Research Methodology & Innovation · Depth: Advanced, long

Summary

Researchers developed a data-driven framework to assess heat vulnerability in Rio de Janeiro's favelas, combining spatially-constrained clustering with land surface temperature (LST) analysis. Utilizing remote sensing and geospatial features, including textural descriptors, spectral indices, and OpenStreetMap road network data, the study identified two distinct favela typologies. Cluster 0 comprises recent, well-connected settlements on flat terrain, while Cluster 1 consists of historical, poorly-connected communities on vegetated slopes. Analysis of 16 extreme heat events, where median LST was $\geq 40^{\circ}$C, revealed systematic temperature differences of 2-3°C between clusters, with flat-terrain favelas (Cluster 0) experiencing significantly higher heat exposure. This framework demonstrates that settlement morphology critically influences heat vulnerability, offering a replicable approach for urban planning and public health interventions in informal settlements globally.

Key takeaway

For AI Scientists developing urban planning tools, this research highlights the critical role of settlement morphology in heat vulnerability. Your models should incorporate spatially-constrained clustering of geospatial features like slope, vegetation, and road networks to accurately identify high-risk informal settlements. This approach enables more targeted public health interventions and urban development strategies, moving beyond generalized vulnerability assessments.

Key insights

Settlement morphology significantly influences heat vulnerability in informal urban areas, with flat-terrain favelas experiencing higher temperatures.

Principles

• Spatially-constrained clustering improves urban typology.
• Vegetation and slope reduce urban heat island effects.
• Road network density correlates with settlement age and heat.

Method

The COP-KMeans algorithm is used for spatially-constrained clustering of favela cells, incorporating must-link constraints based on unique favela identifiers to preserve urban fabric continuity.

In practice

• Use Landsat 8/9 LST data for heat event analysis.
• Integrate OSM road network data for connectivity metrics.
• Merge close favela polygons for accurate complex identification.

Topics

• Heat Vulnerability Assessment
• Spatially-Constrained Clustering
• Rio de Janeiro Favelas
• Land Surface Temperature
• Remote Sensing

Best for: AI Scientist, Research Scientist, Data Scientist

Related on AIssential

• Exploring the potential of AlphaEarth and TESSERA embeddings for Fine-scale Local Climate Zone Mapping: A case study across five cities in Switzerland — Precomputed embeddings from EO foundation models can upscale coarse LCZ maps to 10-m resolution effectively.
• AI data centers are not just energy-hungry—they may be measurably warming the land around them... — AI data centers create "data heat islands," measurably warming surrounding land and impacting millions.
• Deep-time Digital Earth (DDE) linked research significantly undercounts African-led Geoscience Research. — Bibliometric methodologies significantly influence perceived research capacity, shaping policy and funding decisions.
• Building and Road Recognition in Dense Urban Informal Settlements: A Dataset and Benchmark — Existing remote sensing datasets and models are insufficient for accurate infrastructure mapping in dense urban informal settlements.
• Small Data, Big Maps: Training Geospatial ML Models When Samples Are Scarce — Geospatial ML with scarce data demands pragmatic strategies focusing on data quality, appropriate models, and transparent uncertainty.
• CausalPOI: Spatio-Temporal Graph-Based Causal Modeling for Cold-Start POI Check-in Forecasting — CausalPOI uses spatio-temporal causal modeling to predict check-ins for new POIs, outperforming correlation-based methods.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by cs.LG updates on arXiv.org.