What is being touted as the world's most detailed population density map of Africa developed using Artificial Intelligence has been published by researchers who worked with Facebook. The social media company has said that its Boston-based team used advanced computer vision and Machine Learning to combine satellite imagery from Digital Globe with public census data and other sources to create detailed population density maps of Africa.
This is part of Facebook's work with non-profit organizations and research partners to use AI and Big Data to address social, health and infrastructure challenges in Africa.
Facebook Africa population density map.
“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. What’s exciting about projects like these that they provide an opportunity for our company to contribute to these efforts through our expertise in data and machine learning,” said Laura McGorman, Public Policy Manager at Facebook.
Data is something that is generally lacking across Africa. Whether it is accurate population data or Geographic Information System (GIS) data, one generally has to dig really hard to find it if at all.
High-resolution satellite imagery already exists for much of the world. However, prior to Facebook’s mapping project, it would have required countless hours for volunteers to comb through millions of square miles of pictures to identify which contained a tiny town or remote village.
The Facebook team used AI to solve that problem, efficiently crunching through data at a petabyte scale. For Africa alone, for example, the computer vision system examined 11.5 billion individual images to determine whether they contained a building. The team found approximately 110 million buildings in just a few days.
The Facebook population density maps project now aims to keep adding new continents and countries.
Cover image credit: Facebook Africa population density map.Share this article via: