1. Machine Learning Predicted Redox Conditions in the Glacial Aquifer System, Northern Continental United States.
- Author
-
Erickson, M. L., Elliott, S. M., Brown, C. J., Stackelberg, P. E., Ransom, K. M., and Reddy, J. E.
- Subjects
MACHINE learning ,OXIDATION-reduction reaction ,HYDROGEOLOGY ,WATER supply ,AQUIFERS ,GROUNDWATER quality ,ARSENIC ,ALPINE glaciers - Abstract
Groundwater supplies 50% of drinking water worldwide and 30% in the United States. Geogenic and anthropogenic contaminants can, however, compromise water quality, thus limiting groundwater availability. Reduction/oxidation (redox) processes and redox conditions affect groundwater quality by influencing the mobility and transport of common geogenic and anthropogenic contaminants. In the glacial aquifer system, northern United States (GLAC, 1.87 million km2), groundwater with high arsenic or manganese concentration is associated with reducing conditions and high nitrate with oxidizing conditions. This study uses machine learning to identify the relative influence of drivers of redox conditions (e.g., residence time vs. reactivity) across the glacial landscape. We developed three‐dimensional boosted regression tree models to predict redox conditions using the likelihood of low dissolved oxygen or high iron as indicators of anoxic conditions. Results indicate that variation in redox condition is controlled primarily by residence time (e.g., groundwater age and relative depth) and to a lesser extent by geochemical reactivity (e.g., subsurface contact time, soil carbon). Older water and deeper wells, along with more water storage or slower water movement was associated with higher probability of anoxic conditions. Mapped model results illustrate regions where anoxic redox conditions may mobilize geogenic contaminants or oxic conditions may limit denitrification potential. Results may also provide simplified redox input for process or predictive models of, for example, arsenic, manganese, or nitrate. Machine learning modeling methods can lead to improved understanding of contaminant occurrence and what drives redox conditions, and the methods may be transferable to other settings. Plain Language Summary: This study created a three‐dimensional machine learning model, and then maps, of predicted redox conditions in the northern United States system of glacial aquifers. Reduction/oxidation (redox) processes and redox conditions are an important consideration for understanding water availability because redox conditions influence the mobility, transport and toxicity of common geologic‐sourced and human‐produced contaminants (e.g., arsenic and manganese, and nitrate, respectively). Previous studies show that in the northern United States system of glacial aquifers, high arsenic, and manganese concentrations from geologic materials occur primarily in groundwater under reducing conditions. The human‐sourced contaminant nitrate, however, is more common at high concentration in groundwater under more oxidizing conditions. Our model results can be used to better understand the occurrence of common contaminants such as arsenic, manganese, or nitrate—or as simplified redox input to process or other models to more easily and accurately predict contaminants. Key Points: Anoxic conditions, predicted within much of the saturated thickness in some of the study area, influence geogenic contaminant mobilizationOxic conditions, predicted within the entire saturated thickness of large portions of the study area, limit denitrification potentialAnoxic conditions relate to groundwater residence time and chemical reactivity as captured in variables like groundwater age or soil C [ABSTRACT FROM AUTHOR]
- Published
- 2021
- Full Text
- View/download PDF