@unpublished{
 title = {Poverty from Space: Using High-Resolution Satellite Imagery for Estimating Economic Well-Being},
 type = {unpublished},
 year = {2017},
 identifiers = {[object Object]},
 keywords = {machine learning,poverty estimation,satellite imagery},
 websites = {http://elibrary.worldbank.org/doi/book/10.1596/1813-9450-8284},
 month = {12},
 publisher = {The World Bank},
 day = {19},
 series = {Policy Research Working Papers},
 id = {3025185a-2866-3f22-b024-973d53d56d57},
 created = {2018-06-25T15:10:53.204Z},
 accessed = {2018-06-25},
 file_attached = {false},
 profile_id = {35f49df4-e9cf-391e-a76a-8e9e316c42aa},
 group_id = {ee11d323-dd56-3515-8742-9b1e2f0496f7},
 last_modified = {2018-07-02T08:33:32.243Z},
 read = {false},
 starred = {true},
 authored = {false},
 confirmed = {false},
 hidden = {false},
 folder_uuids = {a77eb13c-f2a5-421f-855f-30c90585d1bc,0f486643-3d08-4632-8e8e-e53433d903a9},
 private_publication = {false},
 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.},
 bibtype = {unpublished},
 author = {Engstrom, Ryan and Hersh, Jonathan and Newhouse, David}
}

{"_id":"FMow8oNyfsZWf7RNu","bibbaseid":"engstrom-hersh-newhouse-povertyfromspaceusinghighresolutionsatelliteimageryforestimatingeconomicwellbeing-2017","downloads":0,"creationDate":"2018-06-30T13:35:33.783Z","title":"Poverty from Space: Using High-Resolution Satellite Imagery for Estimating Economic Well-Being","author_short":["Engstrom, R.","Hersh, J.","Newhouse, D."],"year":2017,"bibtype":"unpublished","biburl":null,"bibdata":{"title":"Poverty from Space: Using High-Resolution Satellite Imagery for Estimating Economic Well-Being","type":"unpublished","year":"2017","identifiers":"[object Object]","keywords":"machine learning,poverty estimation,satellite imagery","websites":"http://elibrary.worldbank.org/doi/book/10.1596/1813-9450-8284","month":"12","publisher":"The World Bank","day":"19","series":"Policy Research Working Papers","id":"3025185a-2866-3f22-b024-973d53d56d57","created":"2018-06-25T15:10:53.204Z","accessed":"2018-06-25","file_attached":false,"profile_id":"35f49df4-e9cf-391e-a76a-8e9e316c42aa","group_id":"ee11d323-dd56-3515-8742-9b1e2f0496f7","last_modified":"2018-07-02T08:33:32.243Z","read":false,"starred":"true","authored":false,"confirmed":false,"hidden":false,"folder_uuids":"a77eb13c-f2a5-421f-855f-30c90585d1bc,0f486643-3d08-4632-8e8e-e53433d903a9","private_publication":false,"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.","bibtype":"unpublished","author":"Engstrom, Ryan and Hersh, Jonathan and Newhouse, David","bibtex":"@unpublished{\n title = {Poverty from Space: Using High-Resolution Satellite Imagery for Estimating Economic Well-Being},\n type = {unpublished},\n year = {2017},\n identifiers = {[object Object]},\n keywords = {machine learning,poverty estimation,satellite imagery},\n websites = {http://elibrary.worldbank.org/doi/book/10.1596/1813-9450-8284},\n month = {12},\n publisher = {The World Bank},\n day = {19},\n series = {Policy Research Working Papers},\n id = {3025185a-2866-3f22-b024-973d53d56d57},\n created = {2018-06-25T15:10:53.204Z},\n accessed = {2018-06-25},\n file_attached = {false},\n profile_id = {35f49df4-e9cf-391e-a76a-8e9e316c42aa},\n group_id = {ee11d323-dd56-3515-8742-9b1e2f0496f7},\n last_modified = {2018-07-02T08:33:32.243Z},\n read = {false},\n starred = {true},\n authored = {false},\n confirmed = {false},\n hidden = {false},\n folder_uuids = {a77eb13c-f2a5-421f-855f-30c90585d1bc,0f486643-3d08-4632-8e8e-e53433d903a9},\n private_publication = {false},\n 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.},\n bibtype = {unpublished},\n author = {Engstrom, Ryan and Hersh, Jonathan and Newhouse, David}\n}","author_short":["Engstrom, R.","Hersh, J.","Newhouse, D."],"urls":{"Website":"http://elibrary.worldbank.org/doi/book/10.1596/1813-9450-8284"},"bibbaseid":"engstrom-hersh-newhouse-povertyfromspaceusinghighresolutionsatelliteimageryforestimatingeconomicwellbeing-2017","role":"author","keyword":["machine learning","poverty estimation","satellite imagery"],"downloads":0},"search_terms":["poverty","space","using","high","resolution","satellite","imagery","estimating","economic","well","being","engstrom","hersh","newhouse"],"keywords":["machine learning","poverty estimation","satellite imagery"],"authorIDs":[]}