Poverty Prediction with Public Landsat 7 Satellite Imagery and Machine Learning

TL;DR

This paper demonstrates that publicly available Landsat 7 satellite imagery, despite its lower resolution, can be effectively used with CNNs to predict local economic livelihoods in Africa, achieving high accuracy.

Contribution

The study introduces a method to use free, publicly available Landsat 7 imagery with CNNs for poverty prediction, surpassing previous benchmarks with lower-resolution data.

Findings

CNN models achieve high accuracy with Landsat 7 imagery

Public satellite data can effectively predict local economic conditions

Method reduces reliance on expensive high-resolution imagery

Abstract

Obtaining detailed and reliable data about local economic livelihoods in developing countries is expensive, and data are consequently scarce. Previous work has shown that it is possible to measure local-level economic livelihoods using high-resolution satellite imagery. However, such imagery is relatively expensive to acquire, often not updated frequently, and is mainly available for recent years. We train CNN models on free and publicly available multispectral daytime satellite images of the African continent from the Landsat 7 satellite, which has collected imagery with global coverage for almost two decades. We show that despite these images' lower resolution, we can achieve accuracies that exceed previous benchmarks.