{"ID":2846612,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.01408","arxiv_id":"2511.01408","title":"Leveraging Compact Satellite Embeddings and Graph Neural Networks for Large-Scale Poverty Mapping","abstract":"Accurate, fine-grained poverty maps remain scarce across much of the Global South. While Demographic and Health Surveys (DHS) provide high-quality socioeconomic data, their spatial coverage is limited and reported coordinates are randomly displaced for privacy, further reducing their quality. We propose a graph-based approach leveraging low-dimensional AlphaEarth satellite embeddings to predict cluster-level wealth indices across Sub-Saharan Africa. By modeling spatial relations between surveyed and unlabeled locations, and by introducing a probabilistic \"fuzzy label\" loss to account for coordinate displacement, we improve the generalization of wealth predictions beyond existing surveys. Our experiments on 37 DHS datasets (2017-2023) show that incorporating graph structure slightly improves accuracy compared to \"image-only\" baselines, demonstrating the potential of compact EO embeddings for large-scale socioeconomic mapping.","short_abstract":"Accurate, fine-grained poverty maps remain scarce across much of the Global South. While Demographic and Health Surveys (DHS) provide high-quality socioeconomic data, their spatial coverage is limited and reported coordinates are randomly displaced for privacy, further reducing their quality. We propose a graph-based a...","url_abs":"https://arxiv.org/abs/2511.01408","url_pdf":"https://arxiv.org/pdf/2511.01408v1","authors":"[\"Markus B. Pettersson\",\"Adel Daoud\"]","published":"2025-11-03T10:00:31Z","proceeding":"cs.LG","tasks":"[\"cs.LG\"]","methods":"[\"Graph Neural Network\"]","has_code":false}