Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

Understanding the spatial non-stationarity in the relationships between malaria incidence and environmental risk factors using Geographically Weighted Random Forest : A case study in Rwanda

Nduwayezu, Gilbert LU orcid ; Zhao, Pengxiang LU ; Kagoyire, Clarisse LU ; Eklund, Lina LU ; Bizimana, Jean Pierre LU ; Pilesjö, Petter LU and Mansourian, Ali LU (2023) In Geospatial health 18(1).
Abstract

As found in the health studies literature, the levels of climate association between epidemiological diseases have been found to vary across regions. Therefore, it seems reasonable to allow for the possibility that relationships might vary spatially within regions. We implemented the geographically weighted random forest (GWRF) machine learning method to analyze ecological disease patterns caused by spatially non-stationary processes using a malaria incidence dataset for Rwanda. We first compared the geographically weighted regression (WGR), the global random forest (GRF), and the geographically weighted random forest (GWRF) to examine the spatial non-stationarity in the non-linear relationships between malaria incidence and their risk... (More)

As found in the health studies literature, the levels of climate association between epidemiological diseases have been found to vary across regions. Therefore, it seems reasonable to allow for the possibility that relationships might vary spatially within regions. We implemented the geographically weighted random forest (GWRF) machine learning method to analyze ecological disease patterns caused by spatially non-stationary processes using a malaria incidence dataset for Rwanda. We first compared the geographically weighted regression (WGR), the global random forest (GRF), and the geographically weighted random forest (GWRF) to examine the spatial non-stationarity in the non-linear relationships between malaria incidence and their risk factors. We used the Gaussian areal kriging model to disaggregate the malaria incidence at the local administrative cell level to understand the relationships at a fine scale since the model goodness of fit was not satisfactory to explain malaria incidence due to the limited number of sample values. Our results show that in terms of the coefficients of determination and prediction accuracy, the geographical random forest model performs better than the GWR and the global random forest model. The coefficients of determination of the geographically weighted regression (R2), the global RF (R2), and the GWRF (R2) were 4.74, 0.76, and 0.79, respectively. The GWRF algorithm achieves the best result and reveals that risk factors (rainfall, land surface temperature, elevation, and air temperature) have a strong non-linear relationship with the spatial distribution of malaria incidence rates, which could have implications for supporting local initiatives for malaria elimination in Rwanda.

(Less)
Please use this url to cite or link to this publication:
author
; ; ; ; ; and
organization
publishing date
type
Contribution to journal
publication status
published
subject
keywords
variable importance, partial dependent plot, malaria incidence, geographically weighted random forest, spatial epidemiology, Geographic information system (GIS), Artificial Intelligence (AI), Machine Learning (ML), Geospatial Artificial Intelligence (GeoAI)
in
Geospatial health
volume
18
issue
1
article number
1184
publisher
University of Naples Federico II
external identifiers
  • pmid:37246535
  • scopus:85160564717
ISSN
1970-7096
DOI
10.4081/gh.2023.1184
language
English
LU publication?
yes
id
61ca11f8-be51-4079-b105-b699c9bcd68e
date added to LUP
2023-06-01 09:41:41
date last changed
2025-01-26 02:41:14
@article{61ca11f8-be51-4079-b105-b699c9bcd68e,
  abstract     = {{<p>As found in the health studies literature, the levels of climate association between epidemiological diseases have been found to vary across regions. Therefore, it seems reasonable to allow for the possibility that relationships might vary spatially within regions. We implemented the geographically weighted random forest (GWRF) machine learning method to analyze ecological disease patterns caused by spatially non-stationary processes using a malaria incidence dataset for Rwanda. We first compared the geographically weighted regression (WGR), the global random forest (GRF), and the geographically weighted random forest (GWRF) to examine the spatial non-stationarity in the non-linear relationships between malaria incidence and their risk factors. We used the Gaussian areal kriging model to disaggregate the malaria incidence at the local administrative cell level to understand the relationships at a fine scale since the model goodness of fit was not satisfactory to explain malaria incidence due to the limited number of sample values. Our results show that in terms of the coefficients of determination and prediction accuracy, the geographical random forest model performs better than the GWR and the global random forest model. The coefficients of determination of the geographically weighted regression (R2), the global RF (R2), and the GWRF (R2) were 4.74, 0.76, and 0.79, respectively. The GWRF algorithm achieves the best result and reveals that risk factors (rainfall, land surface temperature, elevation, and air temperature) have a strong non-linear relationship with the spatial distribution of malaria incidence rates, which could have implications for supporting local initiatives for malaria elimination in Rwanda.</p>}},
  author       = {{Nduwayezu, Gilbert and Zhao, Pengxiang and Kagoyire, Clarisse and Eklund, Lina and Bizimana, Jean Pierre and Pilesjö, Petter and Mansourian, Ali}},
  issn         = {{1970-7096}},
  keywords     = {{variable importance; partial dependent plot; malaria incidence; geographically weighted random forest; spatial epidemiology; Geographic information system (GIS); Artificial Intelligence (AI); Machine Learning (ML); Geospatial Artificial Intelligence (GeoAI)}},
  language     = {{eng}},
  month        = {{05}},
  number       = {{1}},
  publisher    = {{University of Naples Federico II}},
  series       = {{Geospatial health}},
  title        = {{Understanding the spatial non-stationarity in the relationships between malaria incidence and environmental risk factors using Geographically Weighted Random Forest : A case study in Rwanda}},
  url          = {{http://dx.doi.org/10.4081/gh.2023.1184}},
  doi          = {{10.4081/gh.2023.1184}},
  volume       = {{18}},
  year         = {{2023}},
}