New algorithm can detect poverty– from space

August 20, 2016 by Chuck Bednar Attempting to locate and assist people living in impoverished parts of the world could be made easier by using satellite imagery and machine learning algorithms, according to a new study led by researchers at Stanford University and published in the journal Science. Traditionally, international aid group perform door-to-door surveys to record data on local incomes in developing nations, but as study author Marshall Burke of the Stanford Institute for Economic Policy Research explained, these methods can be expensive and time consuming. They believe they’ve found a more efficient alternative. What they did, according to BBC News and the Christian Science Monitor, is develop a machine learning algorithm using a computer system to search through millions of satellite images, pinpointing signs of poverty such as poor nighttime lighting and poorly-maintained roads…


Link to Full Article: New algorithm can detect poverty– from space