Intense demand for water in the Central Valley of California and related increases in groundwater nitrate concentration threaten the sustainability of the groundwater resource. To assess contamination risk in the region, we developed a hybrid, non-linear, machine learning model within a statistical learning framework to predict nitrate contamination of groundwater to depths of approximately 500m below ground surface. A database of 145 predictor variables representing well characteristics, historical and current field and landscape-scale nitrogen mass balances, historical and current land use, oxidation/reduction conditions, groundwater flow, climate, soil characteristics, depth to groundwater, and groundwater age were assigned to over 6000 private supply and public supply wells measured previously for nitrate and located throughout the study area. The boosted regression tree (BRT) method was used to screen and rank variables to predict nitrate concentration at the depths of domestic and public well supplies. The novel approach included as predictor variables outputs from existing physically based models of the Central Valley. The top five most important predictor variables included two oxidation/reduction variables (probability of manganese concentration to exceed 50ppb and probability of dissolved oxygen concentration to be below 0.5ppm), field-scale adjusted unsaturated zone nitrogen input for the 1975 time period, average difference between precipitation and evapotranspiration during the years 1971-2000, and 1992 total landscape nitrogen input. Twenty-five variables were selected for the final model for log-transformed nitrate. In general, increasing probability of anoxic conditions and increasing precipitation relative to potential evapotranspiration had a corresponding decrease in nitrate concentration predictions. Conversely, increasing 1975 unsaturated zone nitrogen leaching flux and 1992 total landscape nitrogen input had an increasing relative impact on nitrate predictions. Three-dimensional visualization indicates that nitrate predictions depend on the probability of anoxic conditions and other factors, and that nitrate predictions generally decreased with increasing groundwater age.

Globally, over 200 million people are chronically exposed to arsenic (As) and/or manganese (Mn) from drinking water. We used machine-learning (ML) boosted regression tree (BRT) models to predict high As (>10 μg/L) and Mn (>300 μg/L) in groundwater from the glacial aquifer system (GLAC), which spans 25 states in the northern United States and provides drinking water to 30 million people. Our BRT models’ predictor variables (PVs) included recently developed three-dimensional estimates of a suite of groundwater age metrics, redox condition, and pH. We also demonstrated a successful approach to significantly improve ML prediction sensitivity for imbalanced data sets (small percentage of high values). We present predictions of the probability of high As and high Mn concentrations in groundwater, and uncertainty, at two nonuniform depth surfaces that represent moving median depths of GLAC domestic and public supply wells within the three-dimensional model domain. Predicted high likelihood of anoxic condition (high iron or low dissolved oxygen), predicted pH, relative well depth, several modeled groundwater age metrics, and hydrologic position were all PVs retained in both models; however, PV importance and influence differed between the models. High-As and high-Mn groundwater was predicted with high likelihood over large portions of the central part of the GLAC.

Surveys of microbiological groundwater quality were conducted in a region with intensive animal agriculture in California, USA. The survey included monitoring and domestic wells in eight concentrated animal feeding operations (CAFOs) and 200 small (domestic and community supply district) supply wells across the region. Campylobacter was not detected in groundwater, whereas Escherichia coli O157:H7 and Salmonella were each detected in 2 of 190 CAFO monitoring well samples. Nonpathogenic generic E. coli and Enterococcus spp. were detected in 24.2% (46/190) and 97.4% (185/190) groundwater samples from CAFO monitoring wells and in 4.2% (1/24) and 87.5% (21/24) of CAFO domestic wells, respectively. Concentrations of both generic E. coli and Enterococcus spp. were significantly associated with well depth, season, and the type of adjacent land use in the CAFO. No pathogenic bacteria were detected in groundwater from 200 small supply wells in the extended survey. However, 4.5 to 10.3% groundwater samples were positive for generic E. coli and Enterococcus. Concentrations of generic E. coli were not significantly associated with any factors, but concentrations of Enterococcus were significantly associated with proximity to CAFOs, seasons, and concentrations of potassium in water. Among a subset of E. coli and Enterococcus isolates from both surveys, the majority of E. coli (63.6%) and Enterococcus (86.1%) isolates exhibited resistance to multiple (≥3) antibiotics. Findings confirm significant microbial and antibiotic resistance loading to CAFO groundwater. Results also demonstrate significant attenuative capacity of the unconfined alluvial aquifer system with respect to microbial transport.

No abstract

Groundwater quality is a concern in alluvial aquifers that underlie agricultural areas, such as in the San Joaquin Valley of California. Shallow domestic wells (less than 150 m deep) in agricultural areas are often contaminated by nitrate. Agricultural and rural nitrate sources include dairy manure, synthetic fertilizers, and septic waste. Knowledge of the relative proportion that each of these sources contributes to nitrate concentration in individual wells can aid future regulatory and land management decisions. We show that nitrogen and oxygen isotopes of nitrate, boron isotopes, and iodine concentrations are a useful, novel combination of groundwater tracers to differentiate between manure, fertilizers, septic waste, and natural sources of nitrate. Furthermore, in this work, we develop a new Bayesian mixing model in which these isotopic and elemental tracers were used to estimate the probability distribution of the fractional contributions of manure, fertilizers, septic waste, and natural sources to the nitrate concentration found in an individual well. The approach was applied to 56 nitrate-impacted private domestic wells located in the San Joaquin Valley. Model analysis found that some domestic wells were clearly dominated by the manure source and suggests evidence for majority contributions from either the septic or fertilizer source for other wells. But, predictions of fractional contributions for septic and fertilizer sources were often of similar magnitude, perhaps because modeled uncertainty about the fraction of each was large. For validation of the Bayesian model, fractional estimates were compared to surrounding land use and estimated source contributions were broadly consistent with nearby land use types.

No abstract

A boosted regression tree model was developed to predict pH conditions in three dimensions throughout the glacial aquifer system of the contiguous United States using pH measurements in samples from 18,386 wells and predictor variables that represent aspects of the hydrogeologic setting. Model results indicate that the carbonate content of soils and aquifer materials strongly controls pH and, when coupled with long flowpaths, results in the most alkaline conditions. Conversely, in areas where glacial sediments are thin and carbonate-poor, pH conditions remain acidic. At depths typical of drinking-water supplies, predicted pH >7.5-which is associated with arsenic mobilization-occurs more frequently than predicted pH <6-which is associated with water corrosivity and the mobilization of other trace elements. A novel aspect of this model was the inclusion of numerically based estimates of groundwater flow characteristics (age and flowpath length) as predictor variables. The sensitivity of pH predictions to these variables was consistent with hydrologic understanding of groundwater flow systems and the geochemical evolution of groundwater quality. The model was not developed to provide precise estimates of pH at any given location. Rather, it can be used to more generally identify areas where contaminants may be mobilized into groundwater and where corrosivity issues may be of concern to prioritize areas for future groundwater monitoring.

No abstract