Facebook is using AI to map exactly where Africa’s fast-growing population lives

The population of Africa is growing rapidly. Today, one out of every six people on Earth live in Africa. In 2050, the United Nations “medium scenario” projections predicts one in four humans will live in Africa and in 2100, more than one in three.

But in conversations about Africa especially about development, there are a few consistent talking points – an absence of data. This absence of data hurts African nations in their ability to make good policy and solve problems especially about a lack of infrastructure.

To that end Facebook is using artificial intelligence to map population density around the world with a new type of world map as part of its Connectivity Lab project.

Facebook first analyzed about 20 countries and covered 21.6 million square kilometers in 2016 to help determine how to solve internet connectivity problems for the 10% of the world’s population without access to the internet.

Today’s map is expanded to cover the majority of Africa and is looking to map nearly the entire world’s population. The new map accounts for nearly all of Africa’s 1.3 billion people and their locations down to the meter. The company is hoping to offer the information to everyone from local governments in development planning to aid organizations in hard to reach locations.

Facebook is looking to match census data with structure data taken from satellite imagery to better estimate where people are. “With just the census data, the best you can do is assume that people live everywhere in the district—buildings, fields, and forests alike.” James Gill, an engineer at Facebook explains.

Using a mix of vision techniques, including Facebook’s image-recognition engine, the team was able to identity human-built structures. “But once you know the building locations, you can skip the fields and forests and only allocate the population to the buildings. This gives you very detailed 30-meter by 30-meter population maps.” Gill says.

Already in Tanzania, the new map is being used by providers of renewable electricity to rural areas. Through its high-density population maps with precise data on settlement locations and structures from OpenStreetMap, data was provided to agencies involved in rural electrification, helping mini-grid operators choose the most appropriate locations to begin the work.

In Malawi, the Red Cross and the Missing Maps program, in partnership with the Malawi Ministry of Health, used Facebook maps to inform a measles and rubella campaign. By showing that 97% of land space was uninhabited, the Red Cross was able to deploy 3,000 trained local volunteers to specific areas in need. Continue reading