LINEAR DISCRIMINANT ANALYSIS AS A REGIONAL SCREENING TOOL TO FINGERPRINT SOURCES OF CHLORIDE CONTAMINATION IN GROUNDWATER

Concern over access to safe drinking-water supplies in areas that may be impacted by anthropogenic activities has led to an increasing number of baseline groundwater quality surveys intended to provide context for interpreting water quality data. Flexible screening tools that can parse through these large regional datasets to identify changes in water quality are becoming more important to effectively monitor water supplies. One such tool, developed from previous work by the authors, makes use of linear discriminant analysis (LDA) to identify the most probable source of chloride salinity in groundwater samples based on their geochemical fingerprints. By quantifying the most likely source of chloride salinity, the model provides users a way to assess the impacts of regional development in the context of changing geochemistry. For this work, we applied the LDA model to a dataset of shallow groundwater with known sources of contamination compiled from two studies of groundwater quality in Illinois: Panno et al., Illinois State Geol. Survey, Open File Series 2005-1 and Hwang et al., Environ. & Eng. Geosci., 11: 75-90 (2015). By predicting the source of salinity in groundwater samples for which sources of contamination are known, we validated model predictive-accuracy. Results show high classification accuracy (>80%) for groundwater samples impacted by formation brines or road salt, with diminishing success for samples impacted by organic waste. Posterior probabilities, a statistic inherent to LDA, provides a proxy for prediction confidence that enables the model to be used for assessment and accountability measures. LDA is complementary to fingerprinting using halogen ratios (e.g. Cl/Br) because it implicitly relies on halogen ratios for classification decisions while providing a clearer, more quantitative classification of contamination sources. Our model is ideal for regional assessment or initial screening of salinity sources in shallow groundwater because it makes use of commonly measured solute concentrations in publicly available water quality databases. The validation process highlighted here underscores the importance of testing newly proposed quantitative frameworks under realistic conditions.