OpenStreetMap Features as Proxy to Socio-Economic Indicators: A Network Theory Approach
summary
Uses OpenStreetMap data (points for businesses/establishments, building footprints, road networks, topography, vegetation/water indices) to derive proxy variables for socio-economic conditions. Applies network theory (graph metrics from road/building graphs) and machine learning classification to profile cities/municipalities, and cross-validates results against existing city/municipality tags.
AI-written summary · about
related talks
07mMapping Urban Deprivation
04mUsing OpenStreetMap to create training data
26mMeasuring Economy with Open Earth Observations
48mEmpowering AI Innovation Through Open Geospatial Ecosystems
13mCites Digital Transition to a Sustainable Future: The Role of Data
15mTowards automated mapping of pedestrian path networks at scale
30mLocation Intelligence and Spatial Data Science: from geographic coordinates to business insights
24mBuilding Aggregated Solutions to Scale Your Geospatial Strategies