Record Details

High-resolution poverty maps in Sub-Saharan Africa

Harvard Dataverse (Africa Rice Center, Bioversity International, CCAFS, CIAT, IFPRI, IRRI and WorldFish)

View Archive Info
 
 
Field Value
 
Title High-resolution poverty maps in Sub-Saharan Africa
 
Identifier https://doi.org/10.7910/DVN/5OGWYM
 
Creator Lee, Kamwoo
 
Publisher Harvard Dataverse
 
Description The purpose of this dataset is to provide village-level wealth estimates for places where up-to-date information about geographic wealth distribution is needed. This dataset contains information on buildings, roads, points of interest (POIs), night-time luminosity, population density, and estimated wealth index for 1-mi² inhabited places identified by the underlying datasets. The wealth level is an estimated value of the International Wealth Index which is a comparable asset based wealth index covering the complete developing world.
 
Subject Engineering
Social Sciences
 
Date 2020-12-01
 
Contributor Lee, Kamwoo
 
Type ESRI vector data storage format files
Comma-Separated Values (CSV) files
Graphic images in JPG and PDF files
 
Source This dataset has been created by utilizing publicly available geospatial data and machine learning methods. Method-wise, a new learning mechanism was devised to combine an XGBoost model and a convolutional neural network (CNN) model to estimate wealth index from both geospatial features and satellite images. Data-wise, training data was collected from 6 data sources:

- OpenStreetMap (OSM)

- Demographic and Health Survey (DHS)

- UN OCHA settlements dataset (OCHA)

- Visible Infrared Imaging Radiometer Suite Nighttime Lights (VNL)

- Daytime satellite images through Google Static Maps API (Google Maps)

- High-Resolution Settlement Layer (HRSL) and the WorldPop gridded population dataset (WorldPop).