DeepAI
Log In Sign Up

Towards Sustainable Census Independent Population Estimation in Mozambique

04/26/2021
by   Isaac Neal, et al.
0

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.

READ FULL TEXT
10/06/2021

Census-Independent Population Estimation using Representation Learning

Knowledge of population distribution is critical for building infrastruc...
11/09/2022

Towards Global Crop Maps with Transfer Learning

The continuous increase in global population and the impact of climate c...
06/02/2018

Estimating Local Daytime Population Density from Census and Payroll Data

Daytime population density reflects where people commute and spend their...
09/28/2022

Semantic Segmentation of Vegetation in Remote Sensing Imagery Using Deep Learning

In recent years, the geospatial industry has been developing at a steady...
04/07/2022

So2Sat POP – A Curated Benchmark Data Set for Population Estimation from Space on a Continental Scale

Obtaining a dynamic population distribution is key to many decision-maki...