Mapping local development: What happens when AI meets satellite imagery

Abstract

How can satellite imagery help us understand local poverty? This presentation explains how artificial intelligence summarizes repeated satellite observations as 64 numbers, known as an embedding, that describe patterns on the ground. A separate prediction model learns the relationship between these numbers and measured poverty outcomes. The example focuses on the municipal SDG1 No Poverty index in Bolivia, showing how this approach can support local poverty mapping and why predictions must be checked against measured data. Satellite embeddings do not directly measure poverty, and the resulting estimates complement rather than replace surveys.

Carlos Mendez

Associate Professor of Development Economics

My research interests focus on the integration of development economics, spatial data science, and econometrics to better understand and inform the process of sustainable development across regions.