Working Paper

Poverty from Space : Using High-Resolution Satellite Imagery for Estimating Economic Well-Being

Show simple item record

collection.link.5
https://openknowledge.worldbank.org/handle/10986/9
collection.name.5
Policy Research Working Papers
dc.contributor.author
Engstrom, Ryan
dc.contributor.author
Hersh, Jonathan
dc.contributor.author
Newhouse, David
dc.date.accessioned
2017-12-21T20:28:23Z
dc.date.available
2017-12-21T20:28:23Z
dc.date.issued
2017-12
dc.description.abstract
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.
en
dc.identifier.uri
http://hdl.handle.net/10986/29075
dc.language
English
dc.publisher
World Bank, Washington, DC
dc.relation.ispartofseries
Policy Research Working Paper;No. 8284
dc.rights
CC BY 3.0 IGO
dc.rights.holder
World Bank
dc.rights.uri
http://creativecommons.org/licenses/by/3.0/igo
dc.subject
POVERTY MEASUREMENT
dc.subject
SATELLITE IMAGERY
dc.subject
MACHINE LEARNING
dc.subject
WELL-BEING
dc.subject
POVERTY
dc.title
Poverty from Space
en
dc.title.subtitle
Using High-Resolution Satellite Imagery for Estimating Economic Well-Being
en
dc.type
Working Paper
en
okr.date.disclosure
2017-12-19
okr.doctype
Publications & Research
okr.doctype
Publications & Research :: Policy Research Working Paper
okr.docurl
http://documents.worldbank.org/curated/en/610771513691888412/Poverty-from-space-using-high-resolution-satellite-imagery-for-estimating-economic-well-being
okr.googlescholar.linkpresent
yes
okr.identifier.doi
10.1596/1813-9450-8284
okr.identifier.externaldocumentum
090224b085464805_1_0
okr.identifier.internaldocumentum
29284908
okr.identifier.report
WPS8284
okr.imported
true
en
okr.language.supported
en
okr.pdfurl
http://documents.worldbank.org/curated/en/610771513691888412/pdf/WPS8284.pdf
en
okr.region.administrative
South Asia
okr.region.country
Sri Lanka
okr.topic
Poverty Reduction :: Poverty Assessment
okr.topic
Poverty Reduction :: Poverty Monitoring & Analysis
okr.topic
Poverty Reduction :: Small Area Estimation Poverty Mapping
okr.topic
Science and Technology Development :: Technology Innovation
okr.unit
Poverty and Equity Global Practice

Show simple item record



This item appears in the following Collection(s)