KidSat: satellite imagery to map childhood poverty dataset and benchmark
This provides a standardized benchmark for researchers and policymakers to evaluate satellite-based models for mapping childhood poverty, though it is incremental as it builds on existing datasets and methods.
The authors tackled the lack of standard benchmarks for using satellite imagery to analyze demographic indicators by creating a new dataset pairing satellite imagery with high-quality survey data on child poverty, and they benchmarked multiple models, showing that deep learning foundation models like DINOv2 and SatMAE achieved strong performance with R² scores up to 0.75 in spatial generalization tests.
Satellite imagery has emerged as an important tool to analyse demographic, health, and development indicators. While various deep learning models have been built for these tasks, each is specific to a particular problem, with few standard benchmarks available. We propose a new dataset pairing satellite imagery and high-quality survey data on child poverty to benchmark satellite feature representations. Our dataset consists of 33,608 images, each 10 km $\times$ 10 km, from 19 countries in Eastern and Southern Africa in the time period 1997-2022. As defined by UNICEF, multidimensional child poverty covers six dimensions and it can be calculated from the face-to-face Demographic and Health Surveys (DHS) Program . As part of the benchmark, we test spatial as well as temporal generalization, by testing on unseen locations, and on data after the training years. Using our dataset we benchmark multiple models, from low-level satellite imagery models such as MOSAIKS , to deep learning foundation models, which include both generic vision models such as Self-Distillation with no Labels (DINOv2) models and specific satellite imagery models such as SatMAE. We provide open source code for building the satellite dataset, obtaining ground truth data from DHS and running various models assessed in our work.