Using Satellite Data to Guide Urban Poverty Reduction

Publikation: Bidrag til tidsskrift › Tidsskriftartikel › Forskning › fagfællebedømt

Standard

Using Satellite Data to Guide Urban Poverty Reduction. / Sohnesen, Thomas Pave; Fisker, Peter; Malmgren-Hansen, David.

I: Review of Income and Wealth, Bind 68, Nr. S2 Special Issue, 2022, s. S282-S294.

Publikation: Bidrag til tidsskrift › Tidsskriftartikel › Forskning › fagfællebedømt

Harvard

Sohnesen, TP, Fisker, P & Malmgren-Hansen, D 2022, 'Using Satellite Data to Guide Urban Poverty Reduction', Review of Income and Wealth, bind 68, nr. S2 Special Issue, s. S282-S294. https://doi.org/10.1111/roiw.12552

APA

Sohnesen, T. P., Fisker, P., & Malmgren-Hansen, D. (2022). Using Satellite Data to Guide Urban Poverty Reduction. Review of Income and Wealth, 68(S2 Special Issue), S282-S294. https://doi.org/10.1111/roiw.12552

Vancouver

Sohnesen TP, Fisker P, Malmgren-Hansen D. Using Satellite Data to Guide Urban Poverty Reduction. Review of Income and Wealth. 2022;68(S2 Special Issue):S282-S294. https://doi.org/10.1111/roiw.12552

Author

Sohnesen, Thomas Pave ; Fisker, Peter ; Malmgren-Hansen, David. / Using Satellite Data to Guide Urban Poverty Reduction. I: Review of Income and Wealth. 2022 ; Bind 68, Nr. S2 Special Issue. s. S282-S294.

Bibtex

@article{240684bb05494c279070941643f13c51,
title = "Using Satellite Data to Guide Urban Poverty Reduction",
abstract = "Poverty reduction in low- and middle-income countries is increasingly an urban challenge, and a challenge that continues to be constrained by lack of data, including data on the spatial distribution of poverty within cities. Utilizing existing household survey data in combination with Convolutional Neural Networks (CNN) applied to high-resolution satellite images of cities, this study shows that existing data can generate detailed neighborhood-level maps providing key targeting information for an anti-poverty program. The approach is highly automatic, applicable at scale, and cost-effective. The method also provides direct support for policy development, as illustrated by the case study, where the Government of Mozambique is implementing an urban social safety net program, targeting poor urban neighborhoods, utilizing the estimated poverty maps.",
keywords = "poverty, social protection, remote sensing, convolutional neural networks, image recognition",
author = "Sohnesen, {Thomas Pave} and Peter Fisker and David Malmgren-Hansen",
year = "2022",
doi = "10.1111/roiw.12552",
language = "English",
volume = "68",
pages = "S282--S294",
journal = "Review of Income and Wealth",
issn = "0034-6586",
publisher = "Wiley-Blackwell",
number = "S2 Special Issue",

}

RIS

TY - JOUR

T1 - Using Satellite Data to Guide Urban Poverty Reduction

AU - Sohnesen, Thomas Pave

AU - Fisker, Peter

AU - Malmgren-Hansen, David

PY - 2022

Y1 - 2022

N2 - Poverty reduction in low- and middle-income countries is increasingly an urban challenge, and a challenge that continues to be constrained by lack of data, including data on the spatial distribution of poverty within cities. Utilizing existing household survey data in combination with Convolutional Neural Networks (CNN) applied to high-resolution satellite images of cities, this study shows that existing data can generate detailed neighborhood-level maps providing key targeting information for an anti-poverty program. The approach is highly automatic, applicable at scale, and cost-effective. The method also provides direct support for policy development, as illustrated by the case study, where the Government of Mozambique is implementing an urban social safety net program, targeting poor urban neighborhoods, utilizing the estimated poverty maps.

AB - Poverty reduction in low- and middle-income countries is increasingly an urban challenge, and a challenge that continues to be constrained by lack of data, including data on the spatial distribution of poverty within cities. Utilizing existing household survey data in combination with Convolutional Neural Networks (CNN) applied to high-resolution satellite images of cities, this study shows that existing data can generate detailed neighborhood-level maps providing key targeting information for an anti-poverty program. The approach is highly automatic, applicable at scale, and cost-effective. The method also provides direct support for policy development, as illustrated by the case study, where the Government of Mozambique is implementing an urban social safety net program, targeting poor urban neighborhoods, utilizing the estimated poverty maps.

KW - poverty

KW - social protection

KW - remote sensing

KW - convolutional neural networks

KW - image recognition

U2 - 10.1111/roiw.12552

DO - 10.1111/roiw.12552

M3 - Journal article

VL - 68

SP - S282-S294

JO - Review of Income and Wealth

JF - Review of Income and Wealth

SN - 0034-6586

IS - S2 Special Issue

ER -

ID: 291122513