Paul F. Juckem

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.

Effects of water level and climate on the hydrodynamics and water quality of Anvil Lake, Wisconsin, a shallow seepage lake

ABSTRACT Robertson DM, Juckem PF, Dantoin ED, Winslow LA. 2018. Effects of water level and climate on the hydrodynamics and water quality of Anvil Lake, Wisconsin, a shallow seepage lake. Lake Reserv Manage. 34:00–00. Interannual differences in the water quality of Anvil Lake, Wisconsin, were examined to determine how water level and climate affect the hydrodynamics and trophic state of shallow lakes, and their importance compared to anthropogenic changes in the watershed. Anvil Lake is a relatively pristine seepage lake with hydrology dominated by precipitation, evaporation, and groundwater exchange enabling the typically subtle effects of water level and climate to be evaluated. Groundwater and hydrodynamic models were used to describe lake water and phosphorus budgets and how its hydrodynamics are affected by water level and air temperature. Decreases in water level are expected to cause Anvil Lake and other shallow lakes to stratify fewer days, and have warmer bottom temperatures and more deep-mixing events. Increasing air temperatures should cause these lakes to have shorter ice cover, longer summer stratification periods, and warmer bottom temperatures. How water level affects water quality depends on how nutrient loading and lake volume vary: during drier, low-water years, lakes with large interannual changes in loading should have better water quality, whereas lakes with small changes in loading should degrade slightly. Anthropogenic changes in Anvil Lakes watershed over the past ∼100 yr were about 1.5 times the effects of changes in water level when levels were low, but the effects were similar when levels were high. Climate warming is expected to increase productivity in shallow lakes because warmer air temperatures will likely increase bottom temperatures increasing sediment phosphorus release and deep-mixing events enabling this phosphorus to reach the epilimnion.