Geographically weighted machine learning for predicting the spatial distribution of groundwater nitrate nitrogen (NO3-N) concentration

2025-12-17

Younghun Lee, Changhyun Kim, Hyemin Jeong, Dongho Kim, Byeongwon Lee, Taeseung Park, Seongyun Kim, Dongjin Jeon, Jongho Ahn, Jai-Young Lee, Yoonkyung Cha, Sangchul Lee,
Geographically weighted machine learning for predicting the spatial distribution of groundwater nitrate nitrogen (NO3-N) concentration,
Journal of Hydrology: Regional Studies,
Volume 62,
2025,
102867,
ISSN 2214-5818,
https://doi.org/10.1016/j.ejrh.2025.102867.
(https://www.sciencedirect.com/science/article/pii/S2214581825006962)
Abstract: Study region
This study was conducted on Jeju Island, South Korea, where groundwater serves as a critical water resource and is highly susceptible to contamination from both natural and anthropogenic influences.
Study focus
This study aims to predict the spatial distribution of groundwater nitrate nitrogen (NO3-N) concentrations using geographically weighted random forest (GWRF). The predictive performance and robustness of the GWRF were compared against five conventional machine learning models (CMLMs). Shapley Additive Explanations (SHAP) analysis was employed to quantify the influence of key input variables, categorized into land surface, geological, and anthropogenic factors, on the model predictions.
New hydrological insights for the region
The result showed the superior performance of the GWRF in predicting the spatial distribution of groundwater NO3-N on Jeju Island. Compared to CMLMs, the GWRF provided more accurate and spatially unbiased predictions due to consideration of spatial variability. The SHAP analysis indicated that key factors influencing groundwater NO3-N were average elevation, proportion of heavy clay fields and agricultural areas, and urban areas. These results demonstrated the potential of combining geographically weighted structures with machine learning models in groundwater modeling using geospatial data. Consequently, the findings from this study would help to develop targeted management strategies to mitigate groundwater NO3-N pollution.
Keywords: Groundwater quality; Geospatially weighted machine learning model (GWMLM); Conventional machine learning model (CMLM); Spatial variability