Facebook maps out Africa using artificial intelligence

Simnikiwe Mzekandaba
By Simnikiwe Mzekandaba, IT in government editor
Johannesburg, 11 Apr 2019
Facebook uses its data science skills, and expertise in AI and machine learning to map out local populations.
Facebook uses its data science skills, and expertise in AI and machine learning to map out local populations.

To create the most detailed population density maps of the African continent, Facebook has turned to artificial intelligence (AI) and big data.

According to Facebook, these AI-powered maps aim to support the efforts of humanitarian aid and relief agencies, and are already being used in Sub-Saharan African nations like Malawi and Tanzania.

Facebook's mapping project appears to support one of Deloitte's 2019 technology predictions that large organisations will move towards being AI-fuelled. According to Deloitte, an AI-fuelled company is one in which humans and machines work together within designed digital systems to harness data-driven insights.

As part of the mapping project, the world's biggest social network says it applies the processing muscle of its compute power, data science skills, and expertise in AI and machine learning to map out local populations.

Further, it has partnered with Columbia University's Centre for International Earth Science Information Network to ensure its effort leverages the best available administrative data for all countries involved.

In a statement, Facebook says its Boston-based team uses advanced computer vision and machine learning to combine satellite imagery from Digital Globe with public census data and other sources to create the detailed population density maps.

No Facebook data has been or will be used in the project and the census and satellite data used contain no personally identifiable information, it points out.

"Having started my career at USAID working on malaria control, I have witnessed first-hand the critical role that accurate data plays in the effectiveness of humanitarian efforts," says Laura McGorman, a public policy manager at Facebook.

"What's exciting about projects like these is that they provide an opportunity for our company to contribute to these efforts through our expertise in data and machine learning."

Use cases

Facebook reveals that in Malawi, the Missing Maps Project used the AI-powered maps to filter out the 97% of the terrain that is uninhabited. This, it says, helped to coordinate the efforts of 3 000 Red Cross volunteers in Malawi who visited some 100 000 houses in just three days to educate people about measles and rubella vaccines.

"The maps from Facebook ensure we focus our volunteers' time and resources on the places they're most needed, improving the efficacy of our programmes," says Tyler Radford, executive director of the Humanitarian OpenStreetMap Team, which is part of the Missing Maps Project.

In addition to assisting the Red Cross and Missing Maps Project in Malawi, the maps have been used by aid groups like the Bill and Melinda Gates Foundation, the World Bank and Humanitarian OpenStreetMap.

In Tanzania, the AI-powered maps helped kick-start efforts to bring renewable electrification to rural areas, according to the social media network.

To understand which locations would benefit most from decentralised energy solutions, the Humanitarian OpenStreetMap team travelled to villages identified as high priority on the maps and conducted surveys to understand the population's electricity needs.

The results of these surveys were provided to agencies involved in rural electrification, helping mini-grid operators choose the most appropriate locations to begin the work.

Facebook hopes to add new continents and countries to its population density maps project.

This image represents Facebook's Africa population density map.
This image represents Facebook's Africa population density map.