A new AI tool can track poverty levels in African villages over time by scanning satellite images.
Stanford scholars Marshall Burke, David Lobell and Stefano Ermon have spent the past five years leading a team of researchers to home in on an efficient way to find and track impoverished zones across Africa
The tool searches the images for indicators of development, such as roads, agriculture, housing, and lights turned on at night. Researchers tested the tool on about 20,000 villages across 23 countries in Africa that had existing wealth data.
Professor David Lobel said, “Amazingly, there hasn’t really been any good way to understand how poverty is changing at a local level in Africa. Censuses aren’t frequent enough, and door-to-door surveys rarely return to the same people. If satellites can help us reconstruct a history of poverty, it could open up a lot of room to better understand and alleviate poverty on the continent”.
The team hopes that the tool will help government and NGOs to work out the effectiveness of anti-poverty programs.
No comments:
Post a Comment