Social network giant, Facebook (FB) on Thursday introduced world’s most detailed and advanced ‘population density maps’ using artificial intelligence (AI) for Bangladesh and other countries of Asia Pacific. The maps are 3X more detailed than any other source and will show an estimate of the number of people living within 30-meter grid tiles, and include the number of children under five, as well as the number of women of reproductive age, and other helpful demographics, reports BSS.
FB said this new AI-powered and high-resolution maps would help relief agencies and health organizations better assist people in need, as it is working closely with key non-profit and research partners to use AI and big data to address large-scale social, health and infrastructure challenges in Asia and accelerate achievement of the sustainable development goals (SDGs).
“Building data products from non-personal data sources, like satellite imagery and census data allows FB to share its data science and compute power with the world while protecting privacy,” said the popular social networking site in a media statement. Using its machine learning capabilities, FB started developing population density maps to provide better tools to support connectivity efforts around the world. No FB data is used in the project and the census and satellite data used contain no personally identifiable information.
The latest map for Bangladesh can be downloaded on FB’s page on Humanitarian Data Exchange. FB is applying the processing muscle of its compute power, its extensive data science skills and its expertise in AI. It also partners with Columbia University’s Center for International Earth Science Information Network (CIESIN (http://www.ciesin.org/) to ensure that this effort leverages the best available administrative data for all countries involved.
Prior to FB’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 statement said. The FB team used AI to solve that problem, efficiently crunching through data at a petabyte scale. For instance in a country, the computer vision system examined 11.5 billion individual images to determine whether they contained a building. The team found approximately 110 million building locations in just a few days.
A research manager at FB, Alex Pompe, says that these maps showcase the power of collaboration between FB and top research institutions like Columbia University to combine public data sources and machine learning to empower more data-driven humanitarian projects around the globe.
