Towards Sustainable Census Independent Population Estimation in Mozambique

Isaac Neal, Sohan Seth, Gary Watmough, Mamadou Saliou Diallo

Research output: Contribution to conferencePaperpeer-review

Abstract

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.
Original languageEnglish
Number of pages5
Publication statusPublished - 7 May 2021
EventAI for Public Health Workshop at ICLR 2021 - Online
Duration: 7 May 20217 May 2021
https://aiforpublichealth.github.io/

Conference

ConferenceAI for Public Health Workshop at ICLR 2021
Period7/05/217/05/21
Internet address

Fingerprint

Dive into the research topics of 'Towards Sustainable Census Independent Population Estimation in Mozambique'. Together they form a unique fingerprint.

Cite this