Skip to content Skip to navigation

Could machine learning put impoverished communities back on the map?

Satellite over Earth

To get an accurate measure of whether light intensity can indicate areas with high rates of poverty, Stefano Ermon and his colleagues used machine learning to combine the clues from nighttime light intensity with data from daytime images.

Adobe photos.
Oct 7 2019

Posted In:

Research Spotlights

Satellite images reveal enormous amounts of information about oncoming hurricanes, military troop movements and changes to the polar ice cap.

Research by King Center faculty affiliates Stefano ErmonDavid LobellMarshall Burke, Jeremy Weinstein and Pascaline Dupas can also help us understand and ultimately assist impoverished communities around the world. The multi-disciplinary team leads the Data for Development Initiative at the King Center, and recently embarked on a two-year study that builds on research in which his team created machine learning models to accurately infer poverty and wealth at the community level from satellite imagery. The model used things like nighttime light intensity, as well as features visible during the day, such as roads, tall buildings and even swimming pools, to accurately predict whether homes have access to electricity, piped water and sanitation. The program also predicts crop yields at harvest time and could help identify year-to-year changes that allow farmers to recognize and adapt to climate change.

The approach begins by analyzing images of towns for which there is solid on-the-ground survey information. The program then teaches itself to find visual patterns, from color intensities to edges, that correlate with wealth or access to piped water. Over time, the program gets better at making predictions about social and economic conditions in areas that have no survey data.

The goal is that eventually machine learning could use satellite imagery and on-the-ground data to almost literally put the world’s poorest communities back on the map. That’s important, because there is no accurate or current economic data for many remote communities. Some national governments don’t even want to provide it. That makes it difficult to know which areas need help or even which programs are effective.

Read the full article on the Stanford engineering website.