Poverty from Space : Using High-Resolution Satellite Imagery for Estimating Economic Well-Being
Can features extracted from high spatial resolution satellite imagery accurately estimate poverty and economic well-being? This paper investigates this question by extracting object and texture features from satellite images of Sri Lanka, which are...
| Main Authors: | , , |
|---|---|
| Format: | Working Paper |
| Language: | English |
| Published: |
World Bank, Washington, DC
2017
|
| Subjects: | |
| Online Access: | http://documents.worldbank.org/curated/en/610771513691888412/Poverty-from-space-using-high-resolution-satellite-imagery-for-estimating-economic-well-being http://hdl.handle.net/10986/29075 |
| id |
okr-10986-29075 |
|---|---|
| recordtype |
oai_dc |
| spelling |
okr-10986-290752022-09-17T12:16:45Z Poverty from Space : Using High-Resolution Satellite Imagery for Estimating Economic Well-Being Engstrom, Ryan Hersh, Jonathan Newhouse, David POVERTY MEASUREMENT SATELLITE IMAGERY MACHINE LEARNING WELL-BEING POVERTY Can features extracted from high spatial resolution satellite imagery accurately estimate poverty and economic well-being? This paper investigates this question by extracting object and texture features from satellite images of Sri Lanka, which are used to estimate poverty rates and average log consumption for 1,291 administrative units (Grama Niladhari divisions). The features that were extracted include the number and density of buildings, prevalence of shadows, number of cars, density and length of roads, type of agriculture, roof material, and a suite of texture and spectral features calculated using a nonoverlapping box approach. A simple linear regression model, using only these inputs as explanatory variables, explains nearly 60 percent of poverty headcount rates and average log consumption. In comparison, models built using night-time lights explain only 15 percent of the variation in poverty or income. The predictions remain accurate when restricting the sample to poorer Gram Niladhari divisions. Two sample applications, extrapolating predictions into adjacent areas and estimating local area poverty using an artificially reduced census, confirm the out-of-sample predictive capabilities. 2017-12-21T20:28:23Z 2017-12-21T20:28:23Z 2017-12 Working Paper http://documents.worldbank.org/curated/en/610771513691888412/Poverty-from-space-using-high-resolution-satellite-imagery-for-estimating-economic-well-being http://hdl.handle.net/10986/29075 English Policy Research Working Paper;No. 8284 CC BY 3.0 IGO http://creativecommons.org/licenses/by/3.0/igo World Bank World Bank, Washington, DC Publications & Research Publications & Research :: Policy Research Working Paper South Asia Sri Lanka |
| repository_type |
Digital Repository |
| institution_category |
Foreign Institution |
| institution |
Digital Repositories |
| building |
World Bank Open Knowledge Repository |
| collection |
World Bank |
| language |
English |
| topic |
POVERTY MEASUREMENT SATELLITE IMAGERY MACHINE LEARNING WELL-BEING POVERTY |
| spellingShingle |
POVERTY MEASUREMENT SATELLITE IMAGERY MACHINE LEARNING WELL-BEING POVERTY Engstrom, Ryan Hersh, Jonathan Newhouse, David Poverty from Space : Using High-Resolution Satellite Imagery for Estimating Economic Well-Being |
| geographic_facet |
South Asia Sri Lanka |
| relation |
Policy Research Working Paper;No. 8284 |
| description |
Can features extracted from high spatial
resolution satellite imagery accurately estimate poverty and
economic well-being? This paper investigates this question
by extracting object and texture features from satellite
images of Sri Lanka, which are used to estimate poverty
rates and average log consumption for 1,291 administrative
units (Grama Niladhari divisions). The features that were
extracted include the number and density of buildings,
prevalence of shadows, number of cars, density and length of
roads, type of agriculture, roof material, and a suite of
texture and spectral features calculated using a
nonoverlapping box approach. A simple linear regression
model, using only these inputs as explanatory variables,
explains nearly 60 percent of poverty headcount rates and
average log consumption. In comparison, models built using
night-time lights explain only 15 percent of the variation
in poverty or income. The predictions remain accurate when
restricting the sample to poorer Gram Niladhari divisions.
Two sample applications, extrapolating predictions into
adjacent areas and estimating local area poverty using an
artificially reduced census, confirm the out-of-sample
predictive capabilities. |
| format |
Working Paper |
| author |
Engstrom, Ryan Hersh, Jonathan Newhouse, David |
| author_facet |
Engstrom, Ryan Hersh, Jonathan Newhouse, David |
| author_sort |
Engstrom, Ryan |
| title |
Poverty from Space : Using High-Resolution Satellite Imagery for Estimating Economic Well-Being |
| title_short |
Poverty from Space : Using High-Resolution Satellite Imagery for Estimating Economic Well-Being |
| title_full |
Poverty from Space : Using High-Resolution Satellite Imagery for Estimating Economic Well-Being |
| title_fullStr |
Poverty from Space : Using High-Resolution Satellite Imagery for Estimating Economic Well-Being |
| title_full_unstemmed |
Poverty from Space : Using High-Resolution Satellite Imagery for Estimating Economic Well-Being |
| title_sort |
poverty from space : using high-resolution satellite imagery for estimating economic well-being |
| publisher |
World Bank, Washington, DC |
| publishDate |
2017 |
| url |
http://documents.worldbank.org/curated/en/610771513691888412/Poverty-from-space-using-high-resolution-satellite-imagery-for-estimating-economic-well-being http://hdl.handle.net/10986/29075 |
| _version_ |
1764468431766159360 |