Machine learning to help eradicate world poverty
Scientists at Stanford University, USA, have found a low-cost method to map poverty in areas previously devoid of data, by combining satellite images and making use of machine learning. These improved poverty maps could help organisations and policymakers distribute funds more efficiently and evaluate policies.
One big challenge in providing relief to people living in poverty is locating them. Availability of accurate and reliable information on the location of impoverished zones is surprisingly lacking for much of the world, particularly in African countries. Aid groups and other international organisations often fill in the gaps with door-to-door surveys, but these can be expensive and time-consuming to conduct.
Researchers at Stanford University have used machine learning, which is the science of designing computer algorithms that learn from data, to extract information about poverty from high-resolution satellite imagery.
The team built on earlier machine learning methods to find impoverished areas across five African countries—Nigeria, Tanzania, Uganda, Malawi and Rwanda. Because areas that are brighter at night are usually more developed, the solution involves combining high-resolution daytime imagery with images of Earth at night.