Nighttime Satellite Imagery for poverty Estimation on Village Level

The purpose of this publication is to examine the possibility of estimating poverty at the village level using satellite imagery. The poverty variable used in this publication is the percentage of poor families at the village level. Nighttime satellite imagery (NTL) is used to estimate poverty using XG-Boost and MLP. This study shows that the accuracy and performance of the models vary by province because the NTL data in each province also varies. This study also provides an overview of the relationship between the poverty estimation results at the village level and regional characteristics according to the 2018 PODES data.