The dataset is the output of a model for the rural and urban population distribution on the field, at 1km resolution, and entirely based on public and freely available datasets (WorldPop, Global Land cover 30m, GPWv4, OpenStreet map and the Gazetteer Geonames).

Basically the model subdivides the population in two main categories:

1) People living in agglomerations (from cities to smallest villages)

2) The so called sparse population which is the remaining population living in small villages or isolated placements that cannot be captured by remote sensing or that are not listed in the common gazetteers.

The identification of the agglomeration was done principally by using the artificial surface class from Global Land Cover (GLC 30m resolution) together with Gazetteer punctual data. People allocation is done by using rules for densities and different thresholds based on national values. The sparse population was estimated using relative weights associated with land use classes.