Gridding Forced Displacement using Semi-Supervised Learning

TL;DR

This paper introduces a semi-supervised method to disaggregate refugee data into high-resolution grid cells, combining multiple data sources to reveal localized displacement patterns in Sub-Saharan Africa.

Contribution

It presents a novel semi-supervised approach that integrates diverse datasets to produce high-resolution refugee distribution maps at 0.5-degree grid cells.

Findings

Achieved 92.9% accuracy in refugee placement

Disaggregated over 10 million refugee observations

Revealed localized displacement patterns

Abstract

We present a semi-supervised approach that disaggregates refugee statistics from administrative boundaries to 0.5-degree grid cells across 25 Sub-Saharan African countries. By integrating UNHCR's ProGres registration data with satellite-derived building footprints from Google Open Buildings and location coordinates from OpenStreetMap Populated Places, our label spreading algorithm creates spatially explicit refugee statistics at high granularity.This methodology achieves 92.9% average accuracy in placing over 10 million refugee observations into appropriate grid cells, enabling the identification of localized displacement patterns previously obscured in broader regional and national statistics. The resulting high-resolution dataset provides a foundation for a deeper understanding of displacement drivers.