The State of Brazilian Favelas

This dataset provides a national-scale, harmonized database of all Brazilian favelas delineated by the 2022 Brazilian Census (IBGE), covering 12,344 informal settlements. The dataset integrates census-based socio-demographic and housing indicators with environmental, topographic, pollution, and accessibility variables derived from multiple geospatial sources.

Indicators are organized following a multi-scalar framework (household, within-area, and area-connect levels) and include measures of water supply, sanitation, housing conditions, population characteristics, socio-economic deprivation, land cover, topography, air pollution, and access to health facilities. Four composite indices aligned with UN-Habitat definitions are provided: improved water access, improved sanitation access, sufficient living area, and housing durability.

The dataset also includes cluster labels identifying three infrastructural regimes—Structured, Partially Structured, and Unstructured—derived from unsupervised clustering of the infrastructure indices. All data are spatially referenced to official favela polygons and harmonized to a common coordinate system (SIRGAS 2000).

This dataset supports research on urban inequality, informal settlements, infrastructure provision, environmental exposure, spatial analysis, and machine learning applications, and is directly associated with the codebase available at: https://github.com/dev-jotape/state_of_brazilian_favelas.