Multivariate random forest prediction of poverty and malnutrition prevalence

Advances in remote sensing and machine learning enable increasingly accurate, inexpensive, and timely estimation of poverty and malnutrition indicators to guide development and humanitarian agencies’ programming. However, state of the art models often rely on proprietary data and/or deep or transfer...

Descripción completa

Detalles Bibliográficos
Autores principales: Browne, Chris, Matteson, David S., McBride, Linden, Hu, Leiqiu, Liu, Yanyan, Sun, Ying, Wen, Jiaming, Barrett, Christopher B.
Formato: Journal Article
Lenguaje:Inglés
Publicado: Public Library of Science 2021
Materias:
Acceso en línea:https://hdl.handle.net/10568/142847
_version_ 1855516910309867520
author Browne, Chris
Matteson, David S.
McBride, Linden
Hu, Leiqiu
Liu, Yanyan
Sun, Ying
Wen, Jiaming
Barrett, Christopher B.
author_browse Barrett, Christopher B.
Browne, Chris
Hu, Leiqiu
Liu, Yanyan
Matteson, David S.
McBride, Linden
Sun, Ying
Wen, Jiaming
author_facet Browne, Chris
Matteson, David S.
McBride, Linden
Hu, Leiqiu
Liu, Yanyan
Sun, Ying
Wen, Jiaming
Barrett, Christopher B.
author_sort Browne, Chris
collection Repository of Agricultural Research Outputs (CGSpace)
description Advances in remote sensing and machine learning enable increasingly accurate, inexpensive, and timely estimation of poverty and malnutrition indicators to guide development and humanitarian agencies’ programming. However, state of the art models often rely on proprietary data and/or deep or transfer learning methods whose underlying mechanics may be challenging to interpret. We demonstrate how interpretable random forest models can produce estimates of a set of (potentially correlated) malnutrition and poverty prevalence measures using free, open access, regularly updated, georeferenced data. We demonstrate two use cases: contemporaneous prediction, which might be used for poverty mapping, geographic targeting, or monitoring and evaluation tasks, and a sequential nowcasting task that can inform early warning systems. Applied to data from 11 low and lower-middle income countries, we find predictive accuracy broadly comparable for both tasks to prior studies that use proprietary data and/or deep or transfer learning methods.
format Journal Article
id CGSpace142847
institution CGIAR Consortium
language Inglés
publishDate 2021
publishDateRange 2021
publishDateSort 2021
publisher Public Library of Science
publisherStr Public Library of Science
record_format dspace
spelling CGSpace1428472025-02-24T06:45:19Z Multivariate random forest prediction of poverty and malnutrition prevalence Browne, Chris Matteson, David S. McBride, Linden Hu, Leiqiu Liu, Yanyan Sun, Ying Wen, Jiaming Barrett, Christopher B. models data forecasting surveys remote sensing technology machine learning capacity development malnutrition nutrition poverty Advances in remote sensing and machine learning enable increasingly accurate, inexpensive, and timely estimation of poverty and malnutrition indicators to guide development and humanitarian agencies’ programming. However, state of the art models often rely on proprietary data and/or deep or transfer learning methods whose underlying mechanics may be challenging to interpret. We demonstrate how interpretable random forest models can produce estimates of a set of (potentially correlated) malnutrition and poverty prevalence measures using free, open access, regularly updated, georeferenced data. We demonstrate two use cases: contemporaneous prediction, which might be used for poverty mapping, geographic targeting, or monitoring and evaluation tasks, and a sequential nowcasting task that can inform early warning systems. Applied to data from 11 low and lower-middle income countries, we find predictive accuracy broadly comparable for both tasks to prior studies that use proprietary data and/or deep or transfer learning methods. 2021-09-14 2024-05-22T12:11:10Z 2024-05-22T12:11:10Z Journal Article https://hdl.handle.net/10568/142847 en https://doi.org/10.1002/aepp.13175 Open Access Public Library of Science Browne, Chris; Matteson, David S.; McBride, Linden; Hu, Leiqiu; Liu, Yanyan; Sun, Ying; Wen, Jiaming; Barrett, Christopher B. 2021. Multivariate random forest prediction of poverty and malnutrition prevalence. PLoS ONE 16(9): e0255519 https://doi.org/10.1371/journal.pone.0255519
spellingShingle models
data
forecasting
surveys
remote sensing
technology
machine learning
capacity development
malnutrition
nutrition
poverty
Browne, Chris
Matteson, David S.
McBride, Linden
Hu, Leiqiu
Liu, Yanyan
Sun, Ying
Wen, Jiaming
Barrett, Christopher B.
Multivariate random forest prediction of poverty and malnutrition prevalence
title Multivariate random forest prediction of poverty and malnutrition prevalence
title_full Multivariate random forest prediction of poverty and malnutrition prevalence
title_fullStr Multivariate random forest prediction of poverty and malnutrition prevalence
title_full_unstemmed Multivariate random forest prediction of poverty and malnutrition prevalence
title_short Multivariate random forest prediction of poverty and malnutrition prevalence
title_sort multivariate random forest prediction of poverty and malnutrition prevalence
topic models
data
forecasting
surveys
remote sensing
technology
machine learning
capacity development
malnutrition
nutrition
poverty
url https://hdl.handle.net/10568/142847
work_keys_str_mv AT brownechris multivariaterandomforestpredictionofpovertyandmalnutritionprevalence
AT mattesondavids multivariaterandomforestpredictionofpovertyandmalnutritionprevalence
AT mcbridelinden multivariaterandomforestpredictionofpovertyandmalnutritionprevalence
AT huleiqiu multivariaterandomforestpredictionofpovertyandmalnutritionprevalence
AT liuyanyan multivariaterandomforestpredictionofpovertyandmalnutritionprevalence
AT sunying multivariaterandomforestpredictionofpovertyandmalnutritionprevalence
AT wenjiaming multivariaterandomforestpredictionofpovertyandmalnutritionprevalence
AT barrettchristopherb multivariaterandomforestpredictionofpovertyandmalnutritionprevalence