Overview: Global results from gridfinder model, produced by ESMAP based on joint work with Facebook and others. Uses night-time lights, road networks and existing grid network data to predict the location of transmission and distribution lines globally. Validated in several countries with ~70% accuracy at 1 km. More information: Blog with brief overview: https://blogs.worldbank.org/energy/using-night-lights-map-electrical-gri... Full research paper: https://www.nature.com/articles/s41597-019-0347-4 Visualization: https://gridfinder.org/ The following data are included: grid.gpkg: Vectorized predicted distribution and transmission line network, with existing OpenStreetMap lines tagged in the 'source' column targets.tif: Binary raster showing locations predicted to be connected to distribution grid. lv.tif: Raster of predicted low-voltage infrastructure in kilometres per cell.