Brian P. Austin | Geology Reports

USGS2024

Design and calibration of a nitrate decision support tool for groundwater wells in Wisconsin, USA

This paper describes development of a nitrate decision support tool for groundwater wells (GW-NDST) that combines nitrate leaching and groundwater lag-times to compute well concentrations. The GW-NDST uses output from support models that simulate leached nitrate, groundwater age distributions, and nitrate reduction rates. The support models are linked through convolution to simulate nitrate transport to wells. Spatially distributed parameters were adjusted through calibration to 34,255 nitrate sample targets. Prediction uncertainty is illustrated via Monte Carlo realizations informed during calibration. Over 78% of target concentrations were within the simulated range of results from 450 realizations. An example forecasting scenario illustrates that a range of feasible outcomes exist and should be considered when interpreting forecasts for decision making. Uncertainty in forecasting is unavoidable; the intent of characterizing uncertainty in the GW-NDST is to facilitate decision making by increasing insight into the response of nitrate contamination to physical and chemical processes.

Wisconsin↗

USGS2017

Predicting redox-sensitive contaminant concentrations in groundwater using random forest classification

Machine learning techniques were applied to a large (n > 10,000) compliance monitoring database to predict the occurrence of several redox-active constituents in groundwater across a large watershed. Specifically, random forest classification was used to determine the probabilities of detecting elevated concentrations of nitrate, iron, and arsenic in the Fox, Wolf, Peshtigo, and surrounding watersheds in northeastern Wisconsin. Random forest classification is well suited to describe the nonlinear relationships observed among several explanatory variables and the predicted probabilities of elevated concentrations of nitrate, iron, and arsenic. Maps of the probability of elevated nitrate, iron, and arsenic can be used to assess groundwater vulnerability and the vulnerability of streams to contaminants derived from groundwater. Processes responsible for elevated concentrations are elucidated using partial dependence plots. For example, an increase in the probability of elevated iron and arsenic occurred when well depths coincided with the glacial/bedrock interface, suggesting a bedrock source for these constituents. Furthermore, groundwater in contact with Ordovician bedrock has a higher likelihood of elevated iron concentrations, which supports the hypothesis that groundwater liberates iron from a sulfide-bearing secondary cement horizon of Ordovician age. Application of machine learning techniques to existing compliance monitoring data offers an opportunity to broadly assess aquifer and stream vulnerability at regional and national scales and to better understand geochemical processes responsible for observed conditions.

Water Resources Research↗