Combining satellite imagery and machine learning to predict poverty

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-resolut...

Full description

Saved in:
Bibliographic Details
Published in:Science (American Association for the Advancement of Science) Vol. 353; no. 6301; p. 790
Main Authors: Jean, Neal, Burke, Marshall, Xie, Michael, Alampay Davis, W Matthew, Lobell, David B, Ermon, Stefano
Format: Journal Article
Language:English
Published: United States 19.08.2016
Subjects:
Developing Countries - economics
Humans
Income
Machine Learning
Malawi
Nigeria
Poverty - economics
Rwanda
Satellite Imagery - methods
Tanzania
Uganda
Uganda
Nigeria
Malawi
Rwanda
Tanzania
ISSN:1095-9203, 1095-9203
Online Access:Get more information
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.
Bibliography:ObjectType-Article-2
SourceType-Scholarly Journals-1
ObjectType-Undefined-1
ObjectType-Feature-3
content type line 23
ISSN:1095-9203
1095-9203
DOI:10.1126/science.aaf7894