Hydrogeochemical evolution and driving factors of groundwater quality: based on SOM neural networks and spatial analysis in the mining area, Northern Ordos, China

Coal mining has significant impacts on groundwater environments, often causing changes in hydrogeological conditions and deterioration of water quality, which threaten ecosystem security and domestic water use. In the study area, acid mine drainage is discharged during mining, severely affecting groundwater quality and regional water safety. Conducting water quality research here helps to reveal the impacts of coal mining on groundwater chemistry and provides scientific support for environmental protection and public health. A combination of Self-Organizing Maps (SOM), K-means clustering, hydrogeochemical analysis, and GIS spatial analysis was applied to explore the mechanisms of groundwater quality deterioration and associated health risks. Results indicate that the dominant groundwater hydrochemical types are HCO₃-Ca and HCO₃-Na·Ca types, primarily controlled by water–rock interactions, particularly the dissolution of carbonate and evaporite minerals. Clustering analysis categorized groundwater samples into four distinct groups, Cluster analysis identified four distinct groundwater types. Cluster 1 showed the lowest mineralization but the highest ammonium (NH₄⁺), likely from agricultural or domestic inputs. Cluster 2 was characterized by elevated ion levels, with nitrate (NO₃⁻) contamination being most prominent. Cluster 3 had generally higher ion concentrations, with nitrite (NO₂⁻) as the key indicator. Cluster 4 exhibited the strongest mineralization, with high TDS, sodium (Na⁺), and bicarbonate (HCO₃⁻), reflecting water–rock interaction and evaporative concentration. The water quality assessment indicated that groundwater quality is generally good across most of the study area; however, approximately 2.45% of the region, covering 53.53 km² primarily within and around the mining zones, was classified as poor. Overall, the groundwater system in the Nalin River mining area exhibits a typical pattern of evolution controlled by multiple interacting factors. These findings elucidate the dominant mechanisms governing regional hydrochemical processes and provide scientific guidance and methodological support for groundwater resource protection, pollution prevention, and ecological management in mining regions.