Assessment of groundwater quality variation characteristics and influencing factors in an intensified agricultural area: An integrated hydrochemical and machine learning approach.
Journal:
Journal of environmental management
Published Date:
Nov 6, 2024
Abstract
The decline in groundwater quality in intensive agricultural areas in recent years, driven by environmental change and intensified human activity, poses a significant threat to agricultural production and public health, requiring attention and effective management. However, distinguishing the specific impacts of various factors on groundwater quality remains challenging, which hinders the effective management and prevention of groundwater pollution. This research integrates a hydrochemical analysis with the Entropy-weighted Water Quality Index, Self-Organizing Map (SOM) approach, and Boruta algorithm to investigate groundwater chemical variations and their influencing factors in the Sanjiang Plain, an important grain-producing region in China. The findings reveal that, compared to 2012, the deep groundwater quality has improved, while the shallow groundwater quality has markedly deteriorated. This decline in shallow groundwater quality is primarily attributable to human activities and is characterized by elevated levels of chloride, sulfate, and nitrate and a shift in the groundwater hydrochemical facies from an HCO-Ca·Mg type to a mixed HCO-Ca·Mg and SO·Cl-Ca·Mg type. The SOM results suggested that land use type significantly affects shallow groundwater quality. Further analysis with the Boruta algorithm identified increased sewage and manure emissions from expanding livestock operations as well as enhanced pollutant leakage from the expansion of paddy fields as the primary contributors to the decline in shallow groundwater quality. These findings offer new insights into the mechanisms of groundwater quality changes in agriculturally intensive regions and provide a foundation for improved groundwater pollution management in the Sanjiang Plain and similar areas.