Using Satellite Imagery and Deep Learning to Evaluate the Impact of Anti-Poverty Programs

TL;DR

This paper demonstrates that high-resolution satellite imagery combined with deep learning can effectively evaluate the impact of anti-poverty programs by estimating changes in household welfare, offering a cost-effective alternative to traditional surveys.

Contribution

It introduces a novel method using satellite imagery and deep learning to assess program impact, reducing reliance on costly field surveys in development evaluations.

Findings

Satellite-derived housing quality correlates with household wealth.

The method produces results consistent with traditional survey-based evaluations.

It offers a scalable, inexpensive approach for program impact assessment.

Abstract

The rigorous evaluation of anti-poverty programs is key to the fight against global poverty. Traditional evaluation approaches rely heavily on repeated in-person field surveys to measure changes in economic well-being and thus program effects. However, this is known to be costly, time-consuming, and often logistically challenging. Here we provide the first evidence that we can conduct such program evaluations based solely on high-resolution satellite imagery and deep learning methods. Our application estimates changes in household welfare in the context of a recent anti-poverty program in rural Kenya. The approach we use is based on a large literature documenting a reliable relationship between housing quality and household wealth. We infer changes in household wealth based on satellite-derived changes in housing quality and obtain consistent results with the traditional field-survey based approach. Our approach can be used to obtain inexpensive and timely insights on program effectiveness in international development programs.