Multilevel small-area childhood stunting risk estimation: Insights from spatial ensemble learning, agro-ecological and environmentally remotely sensed indicators
Nduwayezu, Gilbert LU
; Zhao, Pengxiang
LU
; Pilesjö, Petter
LU
; Bizimana, Jean Pierre
LU
and Mansourian, Ali
LU
(2025)
In Environmental and Sustainability Indicators
27.
- Abstract
Small area childhood stunting risk estimations remain a critical tool for shaping the surveillance policies of such a public health concern. With classical statistical methods, stunting risk metrics are mainly reported at a national level, which inhibits fine-scale insights at a more localized level. To this end, we implemented a novel multilevel small area estimation (SAE) approach for effectively explore the scale effect and non-stationarity of cross-sectional stunting prevalence data, by measuring their nonlinear interactions through the lens of satellite-derived indicators, environmental and agroecological factors using a predictive spatial ensemble learning and explainable artificial intelligence framework in the northern province... (More)
Small area childhood stunting risk estimations remain a critical tool for shaping the surveillance policies of such a public health concern. With classical statistical methods, stunting risk metrics are mainly reported at a national level, which inhibits fine-scale insights at a more localized level. To this end, we implemented a novel multilevel small area estimation (SAE) approach for effectively explore the scale effect and non-stationarity of cross-sectional stunting prevalence data, by measuring their nonlinear interactions through the lens of satellite-derived indicators, environmental and agroecological factors using a predictive spatial ensemble learning and explainable artificial intelligence framework in the northern province of Rwanda. We found a wide spatial variability with 27.1 % prevalence in childhood stunting with considerable heterogeneity across regions. Random forest consistently outperformed other base learners, including spatial ensemble learning, with an average F1 score and Matthews Correlation Coefficient of 0.8 and 0.65, respectively. Compared to the observed stunting prevalence, the model respectively resulted in 28.2 %, 30.7 %, 28.2 % and 30.2 % stunting risk at 1 km2 and 5 km2 grid resolutions, village and sector levels evidencing its performance to handle the effect of spatial scale, except the spatial ensemble learning high discriminability between stunting and non-stunting risk probabilities. Our study underscores the influence of livestock intensification and enhanced soil fertility, suggesting the adoption of an integrated farming framework combining the increase of livestock diversity and homestead crops and adapting to climate shocks to improve child health. Our results highlight the need to consider a multilevel framework when planning localized childhood stunting interventions to address persistent stunting risk disparities in the region.
(Less)
- author
- Nduwayezu, Gilbert
LU
; Zhao, Pengxiang
LU
; Pilesjö, Petter
LU
; Bizimana, Jean Pierre
LU
and Mansourian, Ali
LU
- organization
- publishing date
- 2025-09
- type
- Contribution to journal
- publication status
- published
- subject
- keywords
- Childhood stunting, Multilevel small area estimation, Spatial heterogeneity, Spatial ensemble learning, Rwanda
- in
- Environmental and Sustainability Indicators
- volume
- 27
- article number
- 100822
- publisher
- Elsevier
- external identifiers
-
- scopus:105011846127
- DOI
- 10.1016/j.indic.2025.100822
- language
- English
- LU publication?
- yes
- additional info
- Publisher Copyright: © 2025 The Authors
- id
- ce1f55f3-ac72-436c-9c35-0e87af97d9d8
- date added to LUP
- 2025-08-04 21:49:51
- date last changed
- 2025-08-12 16:54:18
@article{ce1f55f3-ac72-436c-9c35-0e87af97d9d8,
abstract = {{<p>Small area childhood stunting risk estimations remain a critical tool for shaping the surveillance policies of such a public health concern. With classical statistical methods, stunting risk metrics are mainly reported at a national level, which inhibits fine-scale insights at a more localized level. To this end, we implemented a novel multilevel small area estimation (SAE) approach for effectively explore the scale effect and non-stationarity of cross-sectional stunting prevalence data, by measuring their nonlinear interactions through the lens of satellite-derived indicators, environmental and agroecological factors using a predictive spatial ensemble learning and explainable artificial intelligence framework in the northern province of Rwanda. We found a wide spatial variability with 27.1 % prevalence in childhood stunting with considerable heterogeneity across regions. Random forest consistently outperformed other base learners, including spatial ensemble learning, with an average F1 score and Matthews Correlation Coefficient of 0.8 and 0.65, respectively. Compared to the observed stunting prevalence, the model respectively resulted in 28.2 %, 30.7 %, 28.2 % and 30.2 % stunting risk at 1 km<sup>2</sup> and 5 km<sup>2</sup> grid resolutions, village and sector levels evidencing its performance to handle the effect of spatial scale, except the spatial ensemble learning high discriminability between stunting and non-stunting risk probabilities. Our study underscores the influence of livestock intensification and enhanced soil fertility, suggesting the adoption of an integrated farming framework combining the increase of livestock diversity and homestead crops and adapting to climate shocks to improve child health. Our results highlight the need to consider a multilevel framework when planning localized childhood stunting interventions to address persistent stunting risk disparities in the region.</p>}},
author = {{Nduwayezu, Gilbert and Zhao, Pengxiang and Pilesjö, Petter and Bizimana, Jean Pierre and Mansourian, Ali}},
keywords = {{Childhood stunting; Multilevel small area estimation; Spatial heterogeneity; Spatial ensemble learning; Rwanda}},
language = {{eng}},
publisher = {{Elsevier}},
series = {{Environmental and Sustainability Indicators}},
title = {{Multilevel small-area childhood stunting risk estimation: Insights from spatial ensemble learning, agro-ecological and environmentally remotely sensed indicators}},
url = {{http://dx.doi.org/10.1016/j.indic.2025.100822}},
doi = {{10.1016/j.indic.2025.100822}},
volume = {{27}},
year = {{2025}},
}