An alternative objective approach has been developed to assess groundwater vulnerability to contamination in Hawaii, combining well capture zones with multiple-variable logistic regression (LR) modelling. The method has been applied to the Pearl Harbor and Honolulu aquifers on Oahu.
Given their isolation, limited storage capacity and irreplaceable uniqueness, freshwater aquifers on oceanic islands are inherently vulnerable to contamination from anthropogenic sources and sea water intrusion. Thus capture zone analysis combined with a subjective susceptibility index is currently used in Hawaii to assess the vulnerability to contamination of drinking water sources derived from groundwater.
In this study, researchers have developed an alternative objective approach that combines well capture zones with multiple-variable logistic regression (LR) modelling, and applied it to the highly utilised Pearl Harbor and Honolulu aquifers on the island of Oahu.
Input for the LR models utilised explanatory variables based on hydrogeology, land use, and well geometry and location. A suite of 11 target contaminants detected in the region – elevated nitrate (>1 mg/L), four chlorinated solvents, four agricultural fumigants, and two pesticides – was used to develop the models.
The ability of the new approach to accurately separate groups of wells with low and high vulnerability was tested, as well as the suitability of nitrate as an indicator of other types of contamination.
The results produced contaminant-specific LR models that accurately identified groups of wells with the lowest/highest reported detections and the lowest/highest nitrate concentrations. Current and former agricultural land uses were identified as significant explanatory variables for eight of the 11 target contaminants, while elevated nitrate was a significant variable for five contaminants.
The utility of the combined approach is contingent on the availability of hydrologic and chemical monitoring data for calibrating groundwater and LR models.
Application of the approach using a reference site with sufficient data could help identify key variables in areas with similar hydrogeology and land use but limited data. In addition, elevated nitrate may also be a suitable indicator of groundwater contamination in areas with limited data.
The objective LR modelling approach developed in this study is flexible enough to address a wide range of contaminants, and represents a useful addition to the current subjective approach.
