Combining satellite imagery and machine learning to predict poverty.

Journal: Science (New York, N.Y.)
PMID: 27540167

Abstract

Reliable data on economic livelihoods remain scarce in the developing world, hampering efforts to study these outcomes and to design policies that improve them. Here we demonstrate an accurate, inexpensive, and scalable method for estimating consumption expenditure and asset wealth from high-resolution satellite imagery. Using survey and satellite data from five African countries--Nigeria, Tanzania, Uganda, Malawi, and Rwanda--we show how a convolutional neural network can be trained to identify image features that can explain up to 75% of the variation in local-level economic outcomes. Our method, which requires only publicly available data, could transform efforts to track and target poverty in developing countries. It also demonstrates how powerful machine learning techniques can be applied in a setting with limited training data, suggesting broad potential application across many scientific domains.

Authors

  • Neal Jean
    Department of Computer Science, Stanford University, Stanford, CA, USA. Department of Electrical Engineering, Stanford University, Stanford, CA, USA.
  • Marshall Burke
    Department of Earth System Science, Stanford University, Stanford, CA, USA. Center on Food Security and the Environment, Stanford University, Stanford, CA, USA. National Bureau of Economic Research, Boston, MA, USA. mburke@stanford.edu.
  • Michael Xie
    Department of Computer Science, Stanford University, Stanford, CA, USA.
  • W Matthew Alampay Davis
    Center on Food Security and the Environment, Stanford University, Stanford, CA, USA.
  • David B Lobell
    Department of Earth System Science, Stanford University, Stanford, CA, USA. Center on Food Security and the Environment, Stanford University, Stanford, CA, USA.
  • Stefano Ermon
    Department of Computer Science, Stanford University, Stanford, CA, USA.

Keywords

External Resources

Popular Topics
Recent Journals