# Global high-resolution estimates of the UN Human Development Index using satellite imagery and machine learning

## TL;DR

This paper uses satellite imagery and machine learning to estimate human development at a much finer global scale than previously possible.

## Contribution

The novel contribution is a generalizable downscaling technique that improves resolution and reveals aggregation bias in human development estimates.

## Key findings

- More than half of the global population was misclassified into the wrong Human Development Index quintile due to aggregation bias.
- The method enables high-resolution estimates for 61,530 municipalities and an 819,309 grid globally.
- Satellite features are published to enhance spatial resolution of administrative data detectable via imagery.

## Abstract

The United Nations Human Development Index, which incorporates income, education and health, is arguably the most widely used alternative to gross domestic product. However, official country-resolution estimates (N=191) limit its use. We build on recent advances in machine learning and satellite imagery to produce and distribute global estimates of the Human Development Index for municipalities (N=61,530) and a 0. 1° × 0. 1° grid (N=819,309). To construct these estimates, we develop and validate a generalizable downscaling technique based on satellite imagery that allows for training and prediction with observations of arbitrary size and shape. We show how our estimates can improve decision-making and that more than half of the global population was previously assigned to the incorrect Human Development Index quintile within each country due to aggregation bias. We publish the satellite features necessary to increase the spatial resolution of any other administrative data that is detectable via imagery.

Survey-based indicators of wellbeing are often available for only large administrative units, like provinces. The authors use satellite-based machine learning models trained on such coarse data to make finer resolution estimates.