Mapping Urban Deprivation
summary
Maps deprived urban areas by combining open geospatial layers and machine learning into a reproducible pipeline that resamples inputs to a 100 m grid for privacy, creates features like building density and POI accessibility from OSM plus vegetation and socioeconomic layers, trains models and tests cross-city transferability, and outputs predicted deprivation maps that both recover known settlements and flag new ones. Models report F1 0.65–0.83 across three cities, with mixed generalization success.
AI-written summary · about
related talks
48mUsing Artificial Intelligence and Satellite Imagery to Zero In on the Philippines’ Most Vulnerable Communities
41mLarge Scale Field Delineation
22mIsland Mapping: Measuring Urban Footprints with Mapillary & Open Source Tools
22mIdentifying Urban Makeshift Communities using satellite imagery and geo-coded data
22mUnderstanding our cities with FOSS4G
22mMessy maps to make sense of a complex world
16mAdvanced Map Techniques (en)
30mOpening Keynote