Disease Prevention Maps

Facebook Disease Prevention Maps are designed to help public health organizations close gaps in understanding where people live, how people are moving, and the state of their cellular connectivity, in order to improve the effectiveness of health campaigns and epidemic response. These datasets, when combined with epidemiological information from health systems, assist nonprofits in reaching vulnerable communities more effectively and in better understanding the pathways of disease outbreaks that are spread by human-to-human contact.

This map shows the density of 3G network coverage availability across areas in the Democratic Republic of Congo affected by the most recent ebola outbreak.

The below map shows the distribution of women of reproductive age (ages 18-49) spread across Tanzania, drawn from a combination of census data and satellite imagery.

Features

Privacy-Preserving

All maps that use Facebook data are aggregated, and privacy-preserving measures are applied.

Global Reach

Movement Maps and Network Coverage Maps are derived from Facebook data that is global in nature.

Timeliness

Our Disease Prevention Maps can be generated quickly as the situation on the ground unfolds. This allows agencies to respond to changing circumstances.

One of the most important pieces of information we need to respond to epidemics is where people are moving. This kind of data can be integrated into our epidemiological models to help us estimate how quickly a disease might spread, and where to put resources to contain it.”

Caroline Buckee, Assistant Professor of Epidemiology, Harvard School of Public Health

Who Uses Disease Prevention Maps

Universities and researchers

Researchers and universities can combine information from health systems with aggregated and anonymous Facebook movement data to glean insights about where the next case of cholera or drug-resistant malaria is likely to occur.

This map shows movement between Greater London and surrounding areas by day. These data are useful to public health...

Map Types

Movement Maps

Aggregate information from people using Facebook on their mobile phones with Location History enabled, showing movement between two points. The methodology can be found here
Network Coverage Maps

Show where people on Facebook have cellular connectivity. All data is privacy-protected, aggregated, and visualized as a polygon of network coverage by speed. More information can be found here
Co-location Maps

These improved co-location insights help researchers better understand general movement patterns like commute patterns, and the probability that people in areas with disease outbreaks will come in contact with new populations. These maps are important to understand the actual chance that a disease will be spread by human-to-human contact.
Travel Patterns

Travel Patterns show comparisons of the number of Facebook users moving large distances, like air or train travel. These comparisons are based only on users who have opted into sharing precise location data from their device with our mobile app through location services. We are initially looking exclusively at international travel. The counts of travel patterns are updated daily. A minimum of 1000 unique location services users is required for us to surface the metric in order to minimize re-identification risk.

Case Studies

We utilize graph representation learning to capitalize on the underlying relationship of population movement with the spread of COVID-19. Specifically, we create a graph where nodes correspond to a... We utilize graph representation learning to capitalize on the underlying relationship of population movement with the spread of COVID-19. Specifically, we create a graph where nodes correspond to a country's regions and the edge weights denote human mobility from one region to another. Then, we employ graph neural networks to predict the number of future cases. Experimental results on 4 European countries demonstrate the superiority of our method.

Disease Prevention Maps

Transfer Graph Neural Networks for Pandemic Forecasting

We utilize graph representation learning to capitalize on the underlying relationship of population movement with the spread of COVID-19. Specifically, we create a graph where nodes correspond to a country's regions and the edge weights denote human mobility from one region to another. Then, we employ graph neural networks to predict the number of future cases. Experimental results on 4 European countries demonstrate the superiority of our method.

Human mobility is a significant factor for disease transmission. Little is known about how the environment influences mobility during a pandemic. The aim of this study was to investigate an effect of... Human mobility is a significant factor for disease transmission. Little is known about how the environment influences mobility during a pandemic. The aim of this study was to investigate an effect of green space on mobility reductions during the early stage of the COVID-19 pandemic in Maryland and California, USA. For 230 minor civil divisions (MCD) in Maryland and 341 census county divisions (CCD) in California, we obtained mobility data from Facebook Data for Good.

Disease Prevention Maps

Relationships between Local Green Space and Human Mobility Patterns during COVID-19 for Maryland and California

Human mobility is a significant factor for disease transmission. Little is known about how the environment influences mobility during a pandemic. The aim of this study was to investigate an effect of green space on mobility reductions during the early stage of the COVID-19 pandemic in Maryland and California, USA. For 230 minor civil divisions (MCD) in Maryland and 341 census county divisions (CCD) in California, we obtained mobility data from Facebook Data for Good.

In collaboration with the Indonesia Ministry of Research and Technology and Indonesia Ministry of Finance, the University of Indonesia developed a Facebook Mobility and Stay At Home Dashboard. The... In collaboration with the Indonesia Ministry of Research and Technology and Indonesia Ministry of Finance, the University of Indonesia developed a Facebook Mobility and Stay At Home Dashboard. The dashboard aims to monitor the social distancing policy's effectiveness and provide recommendations to local and national governments during this pandemic.

Disease Prevention Maps

University of Indonesia Develops Facebook Mobility and Stay At Home Dashboard for Indonesia’s Covid Response

In collaboration with the Indonesia Ministry of Research and Technology and Indonesia Ministry of Finance, the University of Indonesia developed a Facebook Mobility and Stay At Home Dashboard. The dashboard aims to monitor the social distancing policy's effectiveness and provide recommendations to local and national governments during this pandemic.

The use of mobility data by the city of Syracuse from March through June, 2020, is an example of a multi-member collaboration between Harvard researchers in the COVID-19 Mobility Data Network and a... The use of mobility data by the city of Syracuse from March through June, 2020, is an example of a multi-member collaboration between Harvard researchers in the COVID-19 Mobility Data Network and a city-level data team, which was tasked with responsibilities in public health analysis despite not itself sitting within the department of health. Facebook mobility data was integrated into broader situational awareness efforts including an interactive dashboard that was made available to the mayor and others.

Disease Prevention Maps

Digital Mobility Data, Physical Distancing, and COVID-19 in Syracuse

The use of mobility data by the city of Syracuse from March through June, 2020, is an example of a multi-member collaboration between Harvard researchers in the COVID-19 Mobility Data Network and a city-level data team, which was tasked with responsibilities in public health analysis despite not itself sitting within the department of health. Facebook mobility data was integrated into broader situational awareness efforts including an interactive dashboard that was made available to the mayor and others.

In the News

Facebook presenta una iniciativa para ayudar a planificar campañas de salud pública y anticiparse a brotes de enfermedades Spain: Zona Movilidad Facebook lanza mapas de América Latina en alta resolución para ayudar en salud e infraestructura Argentina: Noticias de Taiwan's National Tsing Hua University announces research partnership with Harvard University and Facebook on COVID-19 Central News Agency, Taiwan Gefährliche Freundschaften in Zeiten von Covid-19 Frankfurter Allgemeine Évolution des mobilités et diffusion du Covid-19 en France : ce que les données Facebook dévoilent The Conversation

Get Involved

Check out our high resolution population density maps, including demographic estimates, available for download on the United Nations Office for the Coordination of Humanitarian Affairs (OCHA)’s Humanitarian Data Exchange. Each country-level dataset contains the demographic estimates. If you're interested in working with movement or network coverage maps, please email diseaseprevmaps@fb.com.

Explore

Disease Prevention Maps

Features

Privacy-Preserving

Global Reach

Timeliness

Who Uses Disease Prevention Maps

Universities and researchers

Map Types

Movement Maps

Network Coverage Maps

Co-location Maps

Travel Patterns

Case Studies

Transfer Graph Neural Networks for Pandemic Forecasting

Relationships between Local Green Space and Human Mobility Patterns during COVID-19 for Maryland and California

University of Indonesia Develops Facebook Mobility and Stay At Home Dashboard for Indonesia’s Covid Response

Digital Mobility Data, Physical Distancing, and COVID-19 in Syracuse

In the News

Get Involved