Pakistan Journal of Geology (PJG)

Journal: Pakistan Journal of Geology (PJG)
Author: Ogechukwu H. Obimba, Adeleye Y. B. Anifowose and Kola A. N. Adiat

This is an open access journal distributed under the Creative Commons Attribution License CC BY 4.0, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited

DOI: 10.26480/pjg.01.2026.12.21

Increasing population growth, domestic and agricultural water demand have heightened reliance on groundwater in Gombe and its environs. Proper management of this resource needs both systematic and spatial evaluation. This study integrates Remote Sensing (RS), Geographic Information System (GIS), and the Analytic Hierarchy Process (AHP) to delineate groundwater potential zones in a geologically heterogeneous area. Eight groundwater-influencing parameters: geology, lineament density, slope, drainage density, soil, land use/land cover, elevation, and rainfall were weighted through AHP and analysed in ArcGIS 10.8 to generate groundwater potential map. The resulting map shows a classification of high, moderate, low, and very low potential zones. High-potential zones align with the Gombe, Bima and Sandstone formations, characterized by gentle slopes, lower drainage density, and enhanced fracture development, whereas low￾potential zones are predominantly associated with crystalline basement terrains, which exhibit steep gradients and impervious kerri kerri formation. Model validation using borehole yield data produced an Area under the Curve (AUC) value of 0.84, indicating strong predictive accuracy. The study shows that the integration of RS parameters in GIS and AHP provides a reliable and cost-effective framework for groundwater potential assessment, supporting sustainable groundwater development and management in semi-arid, data-constrained regions. Beyond conventional RS–GIS analysis, this study integrates artificial intelligence techniques specifically the Analytic Hierarchy Process (AHP) for factor weighting and ROC–AUC machine learning validation to enhance predictive accuracy and reduce subjectivity in groundwater potential mapping.