Population Count and Density
Access the data
Have more questions? Contact us
What is Atlas AI’s "Population" layer?
Atlas AI's Population layer provides the count of people (number) and their density (people per square kilometer) for the African continent (52 countries) and India.
What is the spatial and temporal resolution of the Population layer?
| Temporal Extent | 2000 - 2020 |
| Temporal Resolution | Annual |
| Spatial Coverage | African Continent (52 countries) and South Asia unavailable for Afghanistan, Maldives, Mauritius, and Seychelles |
| Spatial Resolution | 1 km x 1 km, with vectorized summary statistics at the national (admin 0), sub-national (admin 1), and local (admin 2 and below) levels of zonal aggregation |
We produce the Population layer for 2000 - 2020 inclusive. Datasets are available in raster format (.tif) at a maximum spatial resolution of 1 km x 1 km in a systematic grid. Summary aggregations at zonal boundary levels such as national (admin 0), sub-national (admin 1), or local (admin 2 and below) available by request in vector format (.shp) or tabular flat files (.csv)
What are the units of measurement for Population?
Density (people per square kilometer) and Count (at chosen level of aggregation)
How does Atlas AI estimate continent-wide Population at high resolution?
Our population estimates are aggregates from three highly regarded and trusted sources: the Global Human Settlement Layer (GHSL), the Gridded Population of World Version 4 (GPW4), and WorldPop.
To calculate total population, we first convert the three input datasets into a single uniform projection system and resolution to standardize them.
For the two years in which we have all three input datasets available (2000 and 2015) we average the standardize input datasets at the pixel level.
For all other years, we first calculate a simple growth rate using WorldPop estimates for each annual interval at the pixel level (e.g. the growth rate between 2000 and 2001 at a given pixel would be calculated as ((WorldPop estimate in 2001 - WorldPop estimate in 2000) / (2001 - 2000)). We then apply these growth rates to the population counts for 2000 and 2015 in order to estimate populations for the horizon 2000 - 2020.
Population densities were obtained from estimated population counts and pixel areas for each year. The area of a pixel depends on the latitude of the pixel.
What are the main data sources we use?
We use the following publicly available data sources for model inputs and validation.
| data source | how we use |
|---|---|
| Global Human Settlement Layer (GHSL) | |
| The GHSL produces global spatial information about the human presence on the planet over time. The project is supported by the European Commission. | We integrate population data from 2000 and 2015 at a 250m resolution. |
| Gridded Population of the World, version 4 (GPWv4) | |
| The GPWv4 was produced by the Center for International Earth Science Information Network at Columbia University with primary support from the National Aeronautics and Space Administration. | We employ population data from 2000, 2005, 2010, 2015, and 2020 at a 30 arc-second (approximately 1km at the equator) resolution. |
| WorldPop | |
| A collaborative effort between organizations, governments, and disciplines, WorldPop provides open and contemporary data on human population distributions. | We integrate population data from 2000 - 2020 at a 3 arc-second (approximately 100m at the equator) resolution. |
How can I learn more?
For more details on the input datasets, we recommend reviewing the published methods for each of the sources: - Global Human Settlement Layer (GHSL) - Gridded Population of the World, version 4 (GPWv4) - WorldPop
Please reach out to us info@atlasai.co if you have trouble accessing the methods descriptions, or have other questions.
How can I explore the data?
Please reach out to us at info@atlasai.co if you have trouble creating a free evaluation account on our proprietary platfrom ApertureTM, or would like to request a free data sample for evaluation prior to purchase.
Access the data
Have more questions? Contact us