2021/04/26 by Isaac Neal, Sohan Seth, Neal, Isaac +5
Mathematics · Social Sciences · #Census and Population Estimation #Demographic Trends and Gender Preferences #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Sex work and related issues
paper · pdf · doi:10.48550/arxiv.2104.12696
openalex publication_date 2021/04/26 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Reliable and frequent population estimation is key for making policies around vaccination and planning infrastructure delivery. Since censuses lack the spatio-temporal resolution required for these tasks, census-independent approaches, using remote sensing and microcensus data, have become popular. We estimate intercensal population count in two pilot districts in Mozambique. To encourage sustainability, we assess the feasibility of using publicly available datasets to estimate population. We also explore transfer learning with existing annotated datasets for predicting building footprints, and training with additional `dot' annotations from regions of interest to enhance these estimations. We observe that population predictions improve when using footprint area estimated with this approach versus only publicly available features.