Poverty mapping in Mongolia with AI-based Ger detection reveals urban slums persist after the COVID-19 pandemic

• DOI: 10.48550/arxiv.2410.09522
• Publication Date: 2024-10-12
• Authors: Jeasurk Yang; Sumin Lee; Sungwon Park; Minjun Lee; Meeyoung Cha
• Keywords: Pandemic; 2019-20 coronavirus outbreak

Mongolia is among the countries undergoing rapid urbanization, and its temporary nomadic dwellings-known as Ger-have expanded into urban areas. Ger settlements in cities are increasingly recognized slums by their socio-economic deprivation. The distinctive circular, tent-like shape of gers enables detection through very-high-resolution satellite imagery. We develop a computer vision algorithm to detect Ulaanbaatar, capital Mongolia, utilizing images collected from 2015 2023. Results reveal that ger have been displaced towards capital's peripheral predicted slum ratio based on our results exhibits significant correlation (r = 0.84) with World Bank's district-level poverty data. Our nationwide extrapolation suggests may continue take up one-fifth population after COVID-19 pandemic, contrary other official predictions anticipated decline. discuss potential machine learning imagery providing insights urbanization patterns monitoring Sustainable Development Goals.