Soil and Aquifer Properties Combine as Predictors of Groundwater Uranium Concentrations within the Central Valley, California

Abstract

With the increasing global need for groundwater resources to fulfill domestic, agricultural, and industrial demands, we face the threat of increasing concentrations of naturally occurring contaminants in water sources and a consequential need to improve our predictive capacity. Here, we combine machine learning and geochemical modeling to reveal the biogeochemical controls on regional groundwater uranium contamination within the Central Valley, California. We use 23 environmental parameters from a statewide groundwater geochemical database and publicly available maps of soil and aquifer physicochemical properties to predict groundwater uranium concentrations by random forest regression. We find that groundwater calcium, nitrate, and sulfate concentrations, soil pH, and clay content (weighted average between 0 and 2 m depths) are the most important predictors of groundwater uranium concentrations. By pairing multivariate partial dependence and accumulated local effect plots with modeled aqueous uranium speciation and surface complexation outputs, we show that regional groundwater uranium exceedances of drinking water standards, 30 μg L–1, are dependent on the formation of uranyl–calcium–carbonato species. The geochemical conditions leading to ternary uranyl complexes within the aquifer are, in part, created by infiltration through the vadose zone, illustrating the critical dependence of groundwater quality on recharge conditions.

Prediction of Soil Heavy Metal Immobilization by Biochar Using Machine Learning

“…Machine learning (ML) can process and learn from large, complex, and multidimensional data to develop predictive models . ML methods such as random forest (RF) and neural networks (NN) have been used to monitor and map contaminants in soils and groundwater . In addition, several studies have utilized ML models to develop risk assessment methods for groundwater pollution, predict the yield and C content of biochar based on biomass properties and pyrolysis conditions, as well as predict the sorption efficiencies of HMs (and metalloids) ,− and personal care products by biochar in water and wastewater.…”

“…16 ML methods such as random forest (RF) and neural networks (NN) have been used to monitor and map contaminants in soils 17 and groundwater. 18 In addition, several studies have utilized ML models to develop risk assessment methods for groundwater pollution, 19 predict the yield and C content of biochar based on biomass properties and pyrolysis conditions, 20 as well as predict the sorption efficiencies of HMs (and metalloids) 16,21−23 and personal care products 24 by biochar in water and wastewater. The ML models used could predict the nonlinear and complex relationships between dependent and independent variables in complex systems for environmental engineering and bioremediation.…”

Patterns in Radon Activity in California Groundwater

“…Lastly, recent work carried out in California’s central valley , proposed a link between human development, including agricultural development and urban expansion, and enhanced downward migration of U in groundwater, and the subsequent increase in U concentration in the water supply. Because U is the parent material of Rn, the anthropogenic redistribution of U may cause an increase in 222 Rn activity in public supply wells.…”

“…Lastly, recent work carried out in California's central valley 61,62 proposed a link between human development, including agricultural development and urban expansion, and enhanced downward migration of U in groundwater, and the subsequent increase in U concentration in the water supply.…”

Statistical learning and uncommon soil microbiota explain biogeochemical responses after wildfire

“…Conservatively, there is on the order of 1 petabyte (PB) of genetic information in a single gram of soil. SL and Machine Learning (ML) are increasingly being applied to gain inference from and to predict complicated behavior and patterns from large datasets [30]. Advancements in statistical theory [31] and the development of more efficient algorithms [32] have helped.…”