Groundwater potential mapping using conventional and machine learning approaches with multi-indicator validation of Aflaj systems in Oman
5 affiliations
- 1Department of Urban Management, Graduate School of Engineering, Kyoto University, Kyoto 615-8245, Japan; Corresponding author.
- 2Disaster Prevention Research Institute (DPRI), Kyoto University, Kyoto 611-0011, Japan
- 3Water Resources Monitoring Department, Ministry of Agriculture, Fisheries and Water Resources, Oman
- 4College of Engineering and Technology, American University of the Middle East, Kuwait
- 5Irrigation Engineering and Hydraulics Department, Alexandria University, Egypt
Abstract
Study region: The Alaqida Basin in northern Oman is an arid mountainous watershed where groundwater is a critical water resource. Groundwater occurrence varies spatially with rainfall, geology, topography, drainage, structural features, soil properties, and land use, highlighting the need for reliable groundwater-potential assessment. Study focus: This study develops a hybrid groundwater-potential zonation framework integrating the Analytic Hierarchy Process (AHP) and Extreme Gradient Boosting (XGBoost). Seven groundwater-conditioning factors—rainfall, geology, soil, slope, drainage density, lineament density, and land use/land cover—were integrated in GIS to generate an AHP-based groundwater-potential map. The resulting classes were used as reference labels to train XGBoost using 40,083 pixel-based samples. Model performance was evaluated using 5-fold spatial block cross-validation and conventional and ordinal classification metrics. New hydrological insights for the region: High and moderate groundwater-potential zones occupy 50.7% of the basin, while low and very low zones account for 45.2% and 4.1%, respectively. XGBoost reproduced the AHP-derived classes with cross-validated accuracy of 0.929, macro F1-score of 0.878, Cohen’s kappa of 0.888, quadratic weighted kappa of 0.941, and Matthews correlation coefficient of 0.889. Low-confidence predictions occupy 5.5% of the basin. Favorable zones coincide with major wadis, coarse alluvial deposits, and structurally enhanced areas, while correspondence with wells, recharge dams, and traditional Aflaj systems provides independent support for the hydrogeological plausibility of the mapped groundwater-potential pattern.
Related
- Heavy metal contamination in groundwater: sources and sustainable remediation approaches: a review.
- Projected increase in stress on African potential groundwater resources due to climate change and increased human water use
- Groundwater Potential Mapping in Northwestern Nigeria: A Comparison of the Analytic Hierarchy Process and Galileo-Enhanced CAT-XGB
- Greenhouse gas mitigation potential of solar photovoltaics: a highly variable indicator within the European Union
- Common challenges and potential approaches in urban soil physics research
BibTeX
@article{aamri2026groundwater,
title = {{Groundwater potential mapping using conventional and machine learning approaches with multi-indicator validation of Aflaj systems in Oman}},
author = {Saif Al Aamri and Sameh Kantoush and Mahmood Al Mamari and Mohamed Saber and Emad Mabrouk and Ahmed Emara},
journal = {Journal of Hydrology: Regional Studies},
year = {2026},
month = oct,
doi = {10.1016/j.ejrh.2026.104090},
url = {https://doi.org/10.1016/j.ejrh.2026.104090},
note = {CC BY},
}
RIS
TY - JOUR
TI - Groundwater potential mapping using conventional and machine learning approaches with multi-indicator validation of Aflaj systems in Oman
AU - Saif Al Aamri
AU - Sameh Kantoush
AU - Mahmood Al Mamari
AU - Mohamed Saber
AU - Emad Mabrouk
AU - Ahmed Emara
PY - 2026
DA - 2026/10/30
JO - Journal of Hydrology: Regional Studies
DO - 10.1016/j.ejrh.2026.104090
UR - https://doi.org/10.1016/j.ejrh.2026.104090
AB - Study region: The Alaqida Basin in northern Oman is an arid mountainous watershed where groundwater is a critical water resource. Groundwater occurrence varies spatially with rainfall, geology, topography, drainage, structural features, soil properties, and land use, highlighting the need for reliable groundwater-potential assessment. Study focus: This study develops a hybrid groundwater-potential zonation framework integrating the Analytic Hierarchy Process (AHP) and Extreme Gradient Boosting (XGBoost). Seven groundwater-conditioning factors—rainfall, geology, soil, slope, drainage density, lineament density, and land use/land cover—were integrated in GIS to generate an AHP-based groundwater-potential map. The resulting classes were used as reference labels to train XGBoost using 40,083 pixel-based samples. Model performance was evaluated using 5-fold spatial block cross-validation and conventional and ordinal classification metrics. New hydrological insights for the region: High and moderate groundwater-potential zones occupy 50.7% of the basin, while low and very low zones account for 45.2% and 4.1%, respectively. XGBoost reproduced the AHP-derived classes with cross-validated accuracy of 0.929, macro F1-score of 0.878, Cohen’s kappa of 0.888, quadratic weighted kappa of 0.941, and Matthews correlation coefficient of 0.889. Low-confidence predictions occupy 5.5% of the basin. Favorable zones coincide with major wadis, coarse alluvial deposits, and structurally enhanced areas, while correspondence with wells, recharge dams, and traditional Aflaj systems provides independent support for the hydrogeological plausibility of the mapped groundwater-potential pattern.
SN - 2214-5818
ER -