On monitoring development indicators using high resolution satellite images

TL;DR

This paper presents a machine learning tool that predicts socio-economic development indicators from high-resolution daytime satellite images, improving accuracy over night light proxies and aiding in monitoring and analysis.

Contribution

The paper introduces a novel machine learning approach for extracting socio-economic indicators from daytime satellite imagery, addressing the challenge of indirect observable features.

Findings

More accurate than night light proxies for socio-economic prediction

Can predict missing data and detect anomalies in development indicators

Used for robustness analysis of stunting in India

Abstract

We develop a machine learning based tool for accurate prediction of socio-economic indicators from daytime satellite imagery. The diverse set of indicators are often not intuitively related to observable features in satellite images, and are not even always well correlated with each other. Our predictive tool is more accurate than using night light as a proxy, and can be used to predict missing data, smooth out noise in surveys, monitor development progress of a region, and flag potential anomalies. Finally, we use predicted variables to do robustness analysis of a regression study of high rate of stunting in India.