Population Density Maps

Our Population Density Maps help nonprofit and multilateral agencies plan vaccination campaigns, respond to natural disasters, and evaluate rural electrification plans. These maps help researchers assess the ways in which climate change and urbanization impact where people live.

Watch Full Video

Features

Our Population Density Maps help nonprofit and multilateral agencies plan vaccination campaigns, respond to natural disasters, and evaluate rural electrification plans. These maps help researchers assess the ways in which climate change and urbanization impact where people live.

In partnership with the Center for International Earth Science Information Network (CIESIN) at Columbia University, we use state-of-the-art computer vision techniques to identify buildings from publicly accessible mapping services to create the world's most accurate population datasets. Our maps are available at 30-meter resolution — much more accurate than existing high-resolution maps, which are only available at a resolution of 100 meters.

Training data through neural networks

To map populations, Facebook's Spatial Computing team trains pattern-recognizing algorithms to identify buildings in commercially available satellite images from Maxar. Using hand-labeled data from diverse areas, these algorithms learn to understand varied landscapes, ensuring extremely accurate modeling anywhere on earth.

Combination with population data

Using building information from Facebook’s analysis, Columbia combines these insights with Census data to generate population estimates, which are then applied to the structures in the satellite imagery. As a final step, the team validates these estimates against more coarse-grained datasets including anonymized household surveys from USAID and the World Bank.

Facebook's high resolution population maps have supported Humanitarian Open Street Map and Missing Maps’ mission of putting the world's most at-risk places on the world…the maps from Facebook ensure we focus our volunteers' time and resources on the places they're most needed, improving the efficacy of our programs.”

Tyler Radford, HumanitarianOpenStreetMap Team

Who uses Population Density Maps

Facebook's high-resolution population density maps have been used by a range of nonprofit and multilateral agencies to plan vaccination campaigns, respond to natural disasters, and assess the feasibility of rural electrification plans. Researchers have also used these layers to analyze trends in urbanization and to assess the impact of climate change on where people live.

Public health institutions

Public health organizations have used these maps to improve the way they reach rural populations with health interventions. For example, in the Democratic Republic of Congo and Mozambique, the Gates Foundation is using Facebook's population maps to improve the way health workers reach households with information about forthcoming vaccine distributions, to procure the right number of vaccines, and to verify the number of children under five to be vaccinated. These maps are also helpful for volunteers distributing bed nets or performing indoor residual spraying for malaria control.

Disaster preparedness and response organizations

Aid organizations have used our settlement layer for disaster preparedness projects, mapping which areas are most likely to be affected by natural disaster and how populations are distributed within those areas.

Rural electrification planners

Rural electrification operators can use our population maps to analyze settlements in urban and rural areas through satellite imagery and prioritize locations for development.

Researchers

Researchers can use the Facebook high resolution settlement layer to help inform development programs that require sub-national population estimates, to understand trends in human mobility, and to accurately quantify urbanization rates.

A high resolution population density map layer for Pretoria, South Africa.

A high resolution population density map layer, for Accra, Ghana.

More Less

Methodology

To create our high-resolution maps, we use machine learning techniques to identify buildings from commercially available satellite images. Then we work with our partners at Columbia University to overlay general population estimates based on publicly available census data and other population statistics. The resulting maps are the most detailed and actionable tools available for aid and research organizations. You can find a tutorial here, which will walk you through the creation of a map and dataset which identifies potential problem areas for COVID-19 vulnerable populations using two publicly available datasets produced by the Facebook Data for Good team.

Learn More

Case Studies

In Indonesia, we’ve been collaborating with the West Java provincial government (Jabar Digital Service) through a combination of advanced data analytics and remote social research to develop a... In Indonesia, we’ve been collaborating with the West Java provincial government (Jabar Digital Service) through a combination of advanced data analytics and remote social research to develop a regional-level aggregate platform. Using Facebook Population Density Maps, we’ve looked into identifying areas in West Java that might potentially have a higher risk for COVID-19 spread, for instance areas densely populated with elderly people, to inform containment strategies especially in rural areas where access to health services are limited.

Population Density Maps

Extending the Art of the Possible with Big Data to Better Inform COVID-19 Responses

In Indonesia, we’ve been collaborating with the West Java provincial government (Jabar Digital Service) through a combination of advanced data analytics and remote social research to develop a regional-level aggregate platform. Using Facebook Population Density Maps, we’ve looked into identifying areas in West Java that might potentially have a higher risk for COVID-19 spread, for instance areas densely populated with elderly people, to inform containment strategies especially in rural areas where access to health services are limited.

Pamoja Trust partnered with Cadasta Foundation providing a list of six locations which are planned to be demolished. Cadasta used geospatial technology to perform analysis, mapping-out the six... Pamoja Trust partnered with Cadasta Foundation providing a list of six locations which are planned to be demolished. Cadasta used geospatial technology to perform analysis, mapping-out the six locations and estimating the residential areas which could be affected. Through this spatial analysis, Cadasta created maps of each of the six locations and identified at-risk residential areas falling within 100, 200 and 500 meters from the planned demolition locations - classified as Extreme Risk (100 m), High Risk (200 m), and Medium Risk (500 m).

Population Density Maps

Rapid Mapping of Areas Marked for Demolitions

Pamoja Trust partnered with Cadasta Foundation providing a list of six locations which are planned to be demolished. Cadasta used geospatial technology to perform analysis, mapping-out the six locations and estimating the residential areas which could be affected. Through this spatial analysis, Cadasta created maps of each of the six locations and identified at-risk residential areas falling within 100, 200 and 500 meters from the planned demolition locations - classified as Extreme Risk (100 m), High Risk (200 m), and Medium Risk (500 m).

We use census data from Bioko Island, in Equatorial Guinea, to evaluate LandScan (LS), WorldPop (WP), and the High-Resolution Settlement Layer (HRSL). Each layer is compared to the gold-standard using... We use census data from Bioko Island, in Equatorial Guinea, to evaluate LandScan (LS), WorldPop (WP), and the High-Resolution Settlement Layer (HRSL). Each layer is compared to the gold-standard using statistical measures to evaluate distribution, error, and bias. We investigated how map choice affects burden estimates from a malaria prevalence model. Specific population layers were able to match the gold-standard distribution at different population densities.

Population Density Maps

Measuring the accuracy of gridded human population density surfaces: a case study in Bioko Island, Equatorial Guinea

We use census data from Bioko Island, in Equatorial Guinea, to evaluate LandScan (LS), WorldPop (WP), and the High-Resolution Settlement Layer (HRSL). Each layer is compared to the gold-standard using statistical measures to evaluate distribution, error, and bias. We investigated how map choice affects burden estimates from a malaria prevalence model. Specific population layers were able to match the gold-standard distribution at different population densities.

Wealthier people in dense neighborhoods can isolate themselves while having amenities and groceries delivered to them. Many can connect remotely to work, and some can even afford to live without... Wealthier people in dense neighborhoods can isolate themselves while having amenities and groceries delivered to them. Many can connect remotely to work, and some can even afford to live without working for a time. But poorer residents of crowded neighborhoods cannot afford such luxuries. They are forced to leave their home every day to go to work, buy groceries, and do laundry. This is especially true in low-income neighborhoods of developing countries – many of which are slums and informal settlements.

Population Density Maps

Cities, crowding, and the coronavirus: Predicting contagion risk hotspots

Wealthier people in dense neighborhoods can isolate themselves while having amenities and groceries delivered to them. Many can connect remotely to work, and some can even afford to live without working for a time. But poorer residents of crowded neighborhoods cannot afford such luxuries. They are forced to leave their home every day to go to work, buy groceries, and do laundry. This is especially true in low-income neighborhoods of developing countries – many of which are slums and informal settlements.

View All Case Studies

In the News

New Asia Pacific Facebook population maps The Australian FB launches world’s most detailed population density maps, including Bangladesh United News of Bangladesh Facebook Bikin Peta Populasi Pakai Artificial Intelligence Indonesia: Viva.co Facebook sáng tạo bản đồ mật độ dân số chi tiết nhất thế giới cho khu vực Châu Á Thái Bình Dương Vietnam: Trainghiemso.vn Facebook lança mapas de densidade populacional de alta resolução do Brasil Brazil: Diariodonordeste Facebook lanza mapas de densidad de población de Latinoamérica Colombia: Guapacho.com Los mapas de densidad poblacional de Facebook Mexico Forbes Facebook divulgó herramienta que visualiza la población de Uruguay con gran precisión El Pais Facebook maps out Africa using artificial intelligence South Africa: ITWeb Facebook artificial intelligence researchers create world’s most detailed population density maps of Africa Zimbabwe: Voice of the People Facebook, AI Researchers Create most Detailed Population Density Maps of Africa Nigeria Communications Week Facebook’s AI team maps the whole population of Africa Kenya: Mipasho AI researchers create density maps of Africa Business Ghana Facebook artificial intelligence (AI) researchers create the world’s most detailed population density maps of Africa Rwanda Podium Facebook is using AI to map exactly where Africa’s fast-growing population lives Ethiopia: Addis Herald Facebook artificial intelligence (AI) researchers create the world’s most detailed population density maps of Africa Somalia: Radio Baidoa

Get Involved

Check out our high resolution population density maps, available for download on the United Nations Office for the Coordination of Humanitarian Affairs (OCHA)’s Humanitarian Data Exchange. To reference this data, please use the following citation: Facebook Connectivity Lab and Center for International Earth Science Information Network - CIESIN - Columbia University. 2016. High Resolution Settlement Layer (HRSL). Source imagery for HRSL © 2016 DigitalGlobe. Accessed DAY MONTH YEAR."

Explore