High-frequency monitoring enables machine learning–based forecasting of acute child malnutrition for early warning

The number of acutely food insecure people worldwide has doubled since 2017, increasing demand for early warning systems (EWS) that can predict food emergencies. Advances in computational methods, and the growing availability of near-real time remote sensing data, suggest that big data approaches mi...

Descripción completa

Detalles Bibliográficos
Autores principales: Constenla-Villoslada, Susana, Liu, Yanyan, McBride, Linden, Ouma, Clinton, Mutanda, Nelson, Barrett, Christopher B.
Formato: Journal Article
Lenguaje:Inglés
Publicado: National Academy of Sciences 2025
Materias:
Acceso en línea:https://hdl.handle.net/10568/175080
_version_ 1855521610152280064
author Constenla-Villoslada, Susana
Liu, Yanyan
McBride, Linden
Ouma, Clinton
Mutanda, Nelson
Barrett, Christopher B.
author_browse Barrett, Christopher B.
Constenla-Villoslada, Susana
Liu, Yanyan
McBride, Linden
Mutanda, Nelson
Ouma, Clinton
author_facet Constenla-Villoslada, Susana
Liu, Yanyan
McBride, Linden
Ouma, Clinton
Mutanda, Nelson
Barrett, Christopher B.
author_sort Constenla-Villoslada, Susana
collection Repository of Agricultural Research Outputs (CGSpace)
description The number of acutely food insecure people worldwide has doubled since 2017, increasing demand for early warning systems (EWS) that can predict food emergencies. Advances in computational methods, and the growing availability of near-real time remote sensing data, suggest that big data approaches might help meet this need. But such models have thus far exhibited low predictive skill with respect to subpopulation-level acute malnutrition indicators. We explore whether updating training data with high frequency monitoring of the predictand can help improve machine learning models’ predictive performance with respect to child acute malnutrition by directly learning the dynamic determinants of rapidly evolving acute malnutrition crises. We combine supervised machine learning methods and remotely sensed feature sets with time series child anthropometric data from EWS’ sentinel sites to generate accurate forecasts of acute malnutrition at operationally meaningful time horizons. These advances can enhance intertemporal and geographic targeting of humanitarian response to impending food emergencies that otherwise have unacceptably high case fatality rates.
format Journal Article
id CGSpace175080
institution CGIAR Consortium
language Inglés
publishDate 2025
publishDateRange 2025
publishDateSort 2025
publisher National Academy of Sciences
publisherStr National Academy of Sciences
record_format dspace
spelling CGSpace1750802025-12-08T10:11:39Z High-frequency monitoring enables machine learning–based forecasting of acute child malnutrition for early warning Constenla-Villoslada, Susana Liu, Yanyan McBride, Linden Ouma, Clinton Mutanda, Nelson Barrett, Christopher B. monitoring machine learning children malnutrition food security early warning systems The number of acutely food insecure people worldwide has doubled since 2017, increasing demand for early warning systems (EWS) that can predict food emergencies. Advances in computational methods, and the growing availability of near-real time remote sensing data, suggest that big data approaches might help meet this need. But such models have thus far exhibited low predictive skill with respect to subpopulation-level acute malnutrition indicators. We explore whether updating training data with high frequency monitoring of the predictand can help improve machine learning models’ predictive performance with respect to child acute malnutrition by directly learning the dynamic determinants of rapidly evolving acute malnutrition crises. We combine supervised machine learning methods and remotely sensed feature sets with time series child anthropometric data from EWS’ sentinel sites to generate accurate forecasts of acute malnutrition at operationally meaningful time horizons. These advances can enhance intertemporal and geographic targeting of humanitarian response to impending food emergencies that otherwise have unacceptably high case fatality rates. 2025-06-10 2025-06-12T15:02:20Z 2025-06-12T15:02:20Z Journal Article https://hdl.handle.net/10568/175080 en Open Access National Academy of Sciences Constenla-Villoslada, Susana; Liu, Yanyan; McBride, Linden; Ouma, Clinton; Mutanda, Nelson; and Barrett, Christopher B. 2025. High-frequency monitoring enables machine learning–based forecasting of acute child malnutrition for early warning. Proceedings of the National Academy of Sciences of the United States of America (PNAS) 122(23): e2416161122. https://doi.org/10.1073/pnas.2416161122
spellingShingle monitoring
machine learning
children
malnutrition
food security
early warning systems
Constenla-Villoslada, Susana
Liu, Yanyan
McBride, Linden
Ouma, Clinton
Mutanda, Nelson
Barrett, Christopher B.
High-frequency monitoring enables machine learning–based forecasting of acute child malnutrition for early warning
title High-frequency monitoring enables machine learning–based forecasting of acute child malnutrition for early warning
title_full High-frequency monitoring enables machine learning–based forecasting of acute child malnutrition for early warning
title_fullStr High-frequency monitoring enables machine learning–based forecasting of acute child malnutrition for early warning
title_full_unstemmed High-frequency monitoring enables machine learning–based forecasting of acute child malnutrition for early warning
title_short High-frequency monitoring enables machine learning–based forecasting of acute child malnutrition for early warning
title_sort high frequency monitoring enables machine learning based forecasting of acute child malnutrition for early warning
topic monitoring
machine learning
children
malnutrition
food security
early warning systems
url https://hdl.handle.net/10568/175080
work_keys_str_mv AT constenlavillosladasusana highfrequencymonitoringenablesmachinelearningbasedforecastingofacutechildmalnutritionforearlywarning
AT liuyanyan highfrequencymonitoringenablesmachinelearningbasedforecastingofacutechildmalnutritionforearlywarning
AT mcbridelinden highfrequencymonitoringenablesmachinelearningbasedforecastingofacutechildmalnutritionforearlywarning
AT oumaclinton highfrequencymonitoringenablesmachinelearningbasedforecastingofacutechildmalnutritionforearlywarning
AT mutandanelson highfrequencymonitoringenablesmachinelearningbasedforecastingofacutechildmalnutritionforearlywarning
AT barrettchristopherb highfrequencymonitoringenablesmachinelearningbasedforecastingofacutechildmalnutritionforearlywarning