Poverty Mapped with Machine Learning, High-res Images

Poverty devastates millions, even in the 21st century. Much of the problem is due to the unknown: the developed world and well-meaning humanitarian groups don’t know where to best employ their resources in the developing world. But clever mapping using machine learning and high-resolution satellite data is a new method proposed by Stanford researchers in the latest issue of Science that could help pinpoint poverty. Five countries in Africa – Malawi, Uganda, Tanzania, Rwanda, and Nigeria – were mapped using the new method. The scientists say the new way to visualize areas most destitute could help direct help where it is most needed. “We have a limited number of surveys conducted in scattered village across the African continent, but otherwise we have very little local-level information on poverty,” said Marshall Burke, an…


Link to Full Article: Poverty Mapped with Machine Learning, High-res Images