Machine learning predictions of nitrate in groundwater used for drinking supply in the conterminous United States

Modelling and mapping of subsurface nitrate-attenuation index in agricultural landscapes

Environmental management of nutrient losses from agricultural lands is required to reduce their potential impacts on the quality of groundwater and eutrophication of surface waters in agricultural landscapes. However, accurate accounting and management of nitrogen losses relies on a robust modelling of nitrogen leaching and its potential attenuation - specifically, the reduction of nitrate to gaseous forms of nitrogen - in subsurface flow pathways. Subsurface denitrification is a key process in potential nitrate attenuation, but the spatial and temporal dynamics of where and when it occurs remain poorly understood, especially at catchment-scale. In this paper, a novel Landscape Subsurface Nitrate-Attenuation Index (LSNAI) is developed to map spatially variable subsurface nitrate attenuation potential of diverse landscape units across the Manawatū-Whanganui region of New Zealand. A large data set of groundwater quality across New Zealand was collated and analysed to assess spatial and temporal variability of groundwater redox status (based on dissolved oxygen, nitrate and dissolved manganese) across different hydrogeological settings. The Extreme Gradient Boosting algorithm was used to predict landscape unit subsurface redox status by integrating the nationwide groundwater redox status data set with various landscape characteristics. Applying the hierarchical clustering analysis and unsupervised classification techniques, the LSNAI was then developed to identify and map five landscape subsurface nitrate attenuation classes, varying from very low to very high potential, based on the predicted groundwater redox status probabilities and identified soil drainage and rock type as key influencing landscape characteristics. Accuracy of the LSNAI mapping was further investigated and validated using a set of independent observations of groundwater quality and redox assessments in shallow groundwaters in the study area. This highlights the potential for further research in up-scaling mapping and modelling of landscape subsurface nitrate attenuation index to accurately account for spatial variability in subsurface nitrate attenuation potential in modelling and assessment of water quality management measures at catchment-scale in agricultural landscapes.

Integrating microbial community dynamics and emerging contaminants (ECs) for precisely quantifying the sources in groundwater affected by livestock farming

Livestock farming is a major emission source of emerging contaminants (ECs); improper management of ECs could lead to severe groundwater pollution. However, research on accurately controlling the impact of large-scale livestock pollution in groundwater and quantifying sources of ECs pollution from livestock farming to formulating effective control measures is scarce. For the first time, the groundwater near four livestock farms (broiler, dairy, aquaculture, and pig farms) was selected as the research object to characterize the ECs, analyze the impact of ECs on microbial communities, and identify the pollution sources of livestock groundwater by the fast expectation-maximization of microbial source tracking (FEAST). Significant differences in the levels of antibiotics and hormones from four livestock farms led to changes in the groundwater microbial communities. The ECs improved the uniqueness of source biomarkers, providing better help for FEAST distinguishing livestock pollution sources at various groundwater mixing ratios. This study improved the accuracy of FEAST in investigating the pollution sources in groundwater and provided experimental evidence for accurate source tracking of ECs in groundwater in large-scale areas heavily polluted by livestock farming.

Drinking water source and exposure to regulated water contaminants in the California Teachers Study cohort

BACKGROUND

Pollutants including metals/metalloids, nitrate, disinfection byproducts, and volatile organic compounds contaminate federally regulated community water systems (CWS) and unregulated domestic wells across the United States. Exposures and associated health effects, particularly at levels below regulatory limits, are understudied.

OBJECTIVE

We described drinking water sources and exposures for the California Teachers Study (CTS), a prospective cohort of female California teachers and administrators.

METHODS

Participants' geocoded addresses at enrollment (1995-1996) were linked to CWS service area boundaries and monitoring data (N = 115,206, 92%); we computed average (1990-2015) concentrations of arsenic, uranium, nitrate, gross alpha (GA), five haloacetic acids (HAA5), total trihalomethanes (TTHM), trichloroethylene (TCE), and tetrachloroethylene (PCE). We used generalized linear regression to estimate geometric mean ratios of CWS exposures across demographic subgroups and neighborhood characteristics. Self-reported drinking water source and consumption at follow-up (2017-2019) were also described.

RESULTS

Medians (interquartile ranges) of average concentrations of all contaminants were below regulatory limits: arsenic: 1.03 (0.54,1.71) µg/L, uranium: 3.48 (1.01,6.18) µg/L, GA: 2.21 (1.32,3.67) pCi/L, nitrate: 0.54 (0.20,1.97) mg/L, HAA5: 8.67 (2.98,14.70) µg/L, and TTHM: 12.86 (4.58,21.95) µg/L. Among those who lived within a CWS boundary and self-reported drinking water information (2017-2019), approximately 74% self-reported their water source as municipal, 15% bottled, 2% private well, 4% other, and 5% did not know/missing. Spatially linked water source was largely consistent with self-reported source at follow-up (2017-2019). Relative to non-Hispanic white participants, average arsenic, uranium, GA, and nitrate concentrations were higher for Black, Hispanic and Native American participants. Relative to participants living in census block groups in the lowest socioeconomic status (SES) quartile, participants in higher SES quartiles had lower arsenic/uranium/GA/nitrate, and higher HAA5/TTHM. Non-metropolitan participants had higher arsenic/uranium/nitrate, and metropolitan participants had higher HAA5/TTHM.

IMPACT

Though average water contaminant levels were mostly below regulatory limits in this large cohort of California women, we observed heterogeneity in exposures across sociodemographic subgroups and neighborhood characteristics. These data will be used to support future assessments of drinking water exposures and disease risk.

Critical role of vegetation and human activity indicators in the prediction of shallow groundwater quality distribution in Jianghan Plain with LightGBM algorithm and SHAP analysis

Groundwater serves as an indispensable resource for freshwater, but its quality has experienced a notable decline over recent decades. Spatial prediction of groundwater quality (GWQ) can effectively assist managers in groundwater remediation, management, and risk control. Based on the traditional intrinsic groundwater vulnerability (IGV) model (DRASTIC) and three vegetation (V) indicators (NDVI, EVI, and kNDVI) and four human activity (H) indicators (land use, GDP, urbanization index, and nighttime light), we constructed four models for GWQ spatial prediction in the Jianghan Plain (JHP), namely DRASTI, DRASTIH, DRASTIV, and DRASTIVH, excluding the conductivity (C) indicator due to its uniformly low values. LightGBM algorithm, Tree-structured Parzen Estimator (TPE) optimization method, and SHapley Additive exPlanations (SHAP) analysis are used for model setting, calibration, and interpretation, respectively. The results show that nitrogen-related GWQ parameters have higher weights, and the model performs exceptionally well when considering all the indicators (accuracy = 0.840, precision = 0.824, recall = 0.832, F1 score = 0.828, AUROC = 0.914). Notably, the introduced indicators (NDVI, EVI, kNDVI, nighttime light, GDP, and urbanization index) rank as the top six in terms of importance, while traditional DRASTI and land use indicators show lower significance. Based on SHAP analysis, poor GWQ primarily occurs in areas with either extremely high or extremely low GDP and urbanization index values, and human activities are the primary cause of poor GWQ in JHP, potentially involving urbanization, industrial and agricultural activities, as well as fertilizer usage. Finally, the methodological framework proposed in this study is encouraged to be applied to diverse regions, such as plains, karst areas, mountainous regions, and coastal areas, to support effective future groundwater management.

Sources and risk factors for nitrate, pathogens, and fecal contamination of private wells in rural southwestern Wisconsin, USA

Household well water can be degraded by contaminants from the land's surface, but private well owners lack means to protect the source water from neighboring disturbances. Rural residents of southwestern Wisconsin, USA, rely on private well water, and the combination of land use and fractured carbonate bedrock makes groundwater vulnerable to contamination. To identify the extent, sources, and risk factors of private well contamination, randomly selected wells sampled during two-day periods in fall (n = 301) and spring (n = 529) were analyzed for nitrate and indicator bacteria, and a subset (n = 138) was sampled across four seasonal events for analysis of pathogens and microbial source tracking markers by quantitative polymerase chain reaction. Risk factors representing land use, hydrology, geology, and well construction were analyzed for associations with contamination in multivariable models. The importance of risk factors varied by contaminant, illustrating the multifaceted nature of rural groundwater quality. Nitrate contamination was associated with agricultural land use, and wells with casings that extended below a shale aquitard accessed less contaminated water than those drawing water from above it. Human fecal microbes were detected in 64 wells (46%), and rainfall was the key risk factor for contamination, indicating that wastewater from septic systems was available to contaminate wells when transport conditions were favorable. Manure microbes from cattle/ruminants and pigs were detected in 33 and 13 wells, respectively, and concentrations increased with the hectarage of cultivated land near wells. Pathogen genes for viruses, bacteria, and protozoa were detected in 66 wells (48%), including more detections of zoonotic than human-specific pathogens, and human Bacteroides, an indicator of wastewater, was an equivocal predictor of pathogen presence in private wells. Characterizing important elements of the setting, like geology, and identifying sources and risk factors for contaminants can inform landscape-level policies to protect groundwater quality.

Research on the traceability and treatment of nitrate pollution in groundwater: a comprehensive review

The preservation of groundwater quality is essential for maintaining the integrity of the water ecological cycle. The preservation of groundwater quality is crucial for sustaining the integrity of the water ecological cycle. Nitrate (NO3-) has emerged as a pervasive contaminant in groundwater, attracting significant research attention due to its extensive distribution and the potential environmental consequences it poses. The primary sources of NO3- pollution include soil organic nitrogen, atmospheric nitrogen deposition, domestic sewage, industrial wastewater, landfill leachate, as well as organic and inorganic nitrogen fertilizers and manure. A comprehensive understanding of these sources is imperative for devising effective strategies to mitigate NO3- contamination. Technologies for tracing NO3--polluted groundwater include hydrochemical analysis, nitrogen and oxygen isotope techniques, microbial tracers, and numerical simulations. Quantitative isotope analysis frequently necessitates the application of mathematical models such as IsoSource, IsoError, IsoConc, MixSIR, SIAR, and MixSIAR to deduce the origins of pollution. This study provides a summary of the application scenarios, as well as the strengths and limitations of these models. In terms of remediation, pump and treat and permeable reactive barrier are predominant technologies currently employed. These approaches are designed to remove or reduce NO3- concentrations in groundwater, thereby restoring its quality. The study offers a systematic examination of NO3- pollution, encompassing its origins, detection methodologies, and remediation approaches, highlighting the role of numerical simulations and integrating multidisciplinary knowledge. Additionally, this review delves into technological advancements and future trends concerning the detection and treatment of NO3- pollution in groundwater. It proposes methods to control the spread of pollution and acts as a guide for identifying and preventing pollution sources.

Recent advances in groundwater pollution research using machine learning from 2000 to 2023: A bibliometric analysis

Groundwater pollution has become a global challenge, posing significant threats to human health and ecological environments. Machine learning, with its superior ability to capture non-linear relationships in data, has shown significant potential in addressing groundwater pollution issues. This review presents a comprehensive bibliometric analysis of 1462 articles published between 2000 and 2023, offering an overview of the current state of research, analyzing development trends, and suggesting future directions. The analysis reveals a growing trend in publications over the 24-year period, with a sharp expansion since 2020. China, the USA, India, and Iran are identified as the leading contributors to publications and citations, with prominent institutions such as Jilin University, the United States Geological Survey, and the University of Tabriz. Moreover, keyword frequency analysis indicates that principal component analysis (PCA) is the most commonly used method, followed by artificial neural network (ANN) and hierarchical clustering analysis (HCA). The most studied groundwater pollutants include nitrate, arsenic, heavy metals, and fluoride. As machine learning has rapidly advanced, research focuses have evolved from fundamental tasks like hydrochemical evolution analysis, water quality index evaluation, and groundwater vulnerability assessments to more complex issues, such as pollutant concentration prediction, pollution risk assessment, and pollution source identification. Despite these advances, challenges related to data quality, data scarcity, model generalization, and interpretability remain. Future research should prioritize data sharing, improving model interpretability, broadening research horizons and advancing theory-guided machine learning. These will enhance our understanding of groundwater pollution mechanisms, and ultimately facilitate more effective pollution control and remediation strategies. In summary, this review provides valuable insights and suggestions for researchers and policymakers working in this critical field.

Integrating machine learning models for optimizing ecosystem health assessments through prediction of nitrate-N concentrations in the lower stretch of Ganga River, India

Nitrate, a highly reactive form of inorganic nitrogen, is commonly found in aquatic environments. Understanding the dynamics of nitrate-N concentration in rivers and its interactions with other water-quality parameters is crucial for effective freshwater ecosystem management. This study uses advanced machine learning models to analyse water quality parameters and predict nitrate-N concentrations in the lower stretch of the Ganga River from the observations of six annual periods (2017 to 2022). The parameters include water temperature, pH, specific conductivity (Sp_Con), dissolved oxygen (DO), nitrate-N, total phosphate (TP), turbidity, biochemical oxygen demand (BOD), silicate, total dissolved solids (TDS), and rainfall. The present study evaluated the predictive performance of five models-Multiple Polynomial Regression (MPR), Generalized Additive Models (GAMs), Decision Tree Regression, Random Forest (RF), and XGBoost (Extreme Gradient Boosting)-using RMSE, MAE, MAPE, NSE and R2 metrics. XGBoost emerged as the top performer, with an RMSE of 0.024, MAE of 0.018, MAPE of 51.805, NSE of 0.855 and R2 of 0.85, explaining 85% of the variance in nitrate-N concentrations. Random Forest also demonstrated strong predictive capability, with an RMSE of 0.028, MAE of 0.021, MAPE of 57.272, NSE of 0.804 and R2 of 0.80. MPR effectively modelled non-linear relationships, explaining 75% of the variance, while Decision Tree Regression and GAMs were less effective, with R2 values of 0.60 and 0.48, respectively. Variables (BOD, pH, Rainfall, water temperature, and total phosphate) were the best predictors of nitrate-N dynamics. Comparative analysis with previous studies confirmed the robustness of XGBoost and Random Forest in environmental data modelling. The findings highlight the importance of advanced machine learning models in accurately predicting water quality parameters and facilitating proactive management strategies.

Reducing Uncertainty of Groundwater Redox Condition Predictions at National Scale, for Decision Making and Policy

Understanding hydrogeochemical heterogeneity, associated with natural nitrate attenuation, is an integral part of implementing integrated land and water management on a regional or national scale. Redox conditions are a key indicator of naturally occurring denitrification in the groundwater environment, and often used to inform spatial planning and targeted regulation. This work describes the development of a statistical redox condition model for the groundwater environment at a national scale, using spatially variable physiochemical descriptors as predictors. The proposed approach builds on previous work, by complementing the available data with expert knowledge, in the form of synthetic data. Special care is given so that the synthetic data do not overfit and create further imbalances to the training dataset. The predictor dataset is further complemented by the results of a data driven model of the water table developed for this study, which is used both as a predictive parameter and a reference level for groundwater redox condition predictions at different depths. The developed model predicted the redox class for 84% of the samples in the out-of-bag datasets. We also propose an alternative approach for the communication of prediction uncertainty. We use the concept of a discriminate function to identify model classifications that may be ambiguous. Our results show a marked reduction in prediction uncertainty at shallow depths, with uncertainty in reduced environments decreasing from 76 to 12%, and overall uncertainty reduced by approximately 20%, though improvements at greater depths are less pronounced. We conclude that this approach can highlight robust model predictions that are defendable for decision making and can identify areas where monitoring or sampling efforts can be focused for improved outcomes.

Small-data-trained model for predicting nitrate accumulation in one-stage partial nitritation-anammox processes controlled by oxygen supply rate

Nitrate (NO3--N) accumulation is the biggest obstacle for wastewater treatment via partial nitritation-anammox process. Dissolved oxygen (DO) control is the most used strategy to prevent NO3--N accumulation, but the performance is usually unstable. This study proposes a novel strategy for controlling NO3--N accumulation based on oxygen supply rate (OSR). In comparison, limiting the OSR is more effective than limiting DO in controlling NO3--N accumulation through mathematical simulation. A laboratory-scale one-stage partial nitritation-anammox system was continuously operated for 135 days, which was divided into five stages with different OSRs. A novel deep learning model integrating Gated Recurrent Unit and Multilayer Perceptron was developed to predict NO3--N accumulation load. To tackle with the general obstacle of limited environmental samples, a generic evaluation was proposed to optimise the model structure by leveraging predictive performance and overfitting risk. The developed model successfully predicted the NO3--N accumulation in the system ten days in advance, showcasing its potential contribution to system design and performance enhancement.

Drinking private well water: Groundwater quality and management of wells in southern Alabama

Private wells provide a source of household water for over 40 million people in the United States and an estimated 1 million people in the Coastal Lowlands Aquifer system along the Gulf of Mexico. Well water quality is dependent on the local geology and factors that contribute to anthropogenic contamination from the surface. Here, we evaluated groundwater quality and well management in southern Alabama, USA, to better understand factors that influence exposures through drinking water from private wells. The most common constituents that exceeded USEPA primary or secondary human health benchmarks were pH (92%), and total coliform (TC) (25%), followed by Fe (7%), Pb (6%), nitrate (1%), and As (1%). Most wells (68%) also displayed temporal changes in the number of exceedances, often showing positive for TC during one sampling campaign and negative in another, while the secondary standard for pH (6.5-8.5) was consistently not met. We also found that the common choices of water treatment did not protect against the most common water quality exceedances. Our results underscore the need to understand well water quality coupled with management practices when assessing potential exposures to the private well population through drinking water.

Impact of climate change and land management on nitrate pollution in the high plains aquifer

High concentrations of nitrate in groundwater pose risks to human and environmental health. This study evaluates the potential impact of climate change, land use, and fertilizer application rates on groundwater nitrate levels in the High Plains Aquifer under four Shared Socioeconomic Pathway (SSP) scenarios. A random forest model, with predictors such as fertilizer application rates, cropland coverage, and climate variables from six Coupled Model Intercomparison Project models, is used to project future nitrate concentrations. Results show increases across all scenarios, with nitrate levels rising by 4% under SSP5-8.5 and up to 13% under SSP2-4.5 when accounting for climate change effects. Fertilizer application rates are identified as the primary driver of projected changes. The northern and central regions of the aquifer exhibited the most pronounced increases. The projected changes in nitrate levels, observed across both low- and high-greenhouse gas emission pathways, highlight the need to develop integrated management strategies that consider shared socioeconomic scenarios and water resource protection constraints.

Comparison and prediction of shallow groundwater nitrate in Shaying River basin based on urban distribution using multiple machine learning approaches

Groundwater, a pivotal water resource in numerous regions worldwide, confronts formidable challenges posed by severe nitrate pollution. Traditional research methodologies aimed at addressing groundwater nitrate contamination frequently struggle to accurately depict the intricate conditions of the groundwater environment, particularly when dealing with high variability and nonlinear data. However, the advent of machine learning (ML) has heralded an innovative approach to simulating groundwater dynamics. In this study, six ML algorithms were deployed to model the concentrations of shallow groundwater nitrates in the Shaying River Basin. The efficacy of each model was assessed through comprehensive metrics including the coefficient of determination (R2), mean absolute error (MAE), and root mean square error (RMSE), gauging the alignment between observed and predicted groundwater nitrate levels. Subsequently, to discern the principal environmental factors influencing NO3-N concentrations, the most proficient model was selected. Among the array of models, the XGB algorithm, renowned for its capacity to handle extreme values, demonstrated superior performance (R2 = 0.773, MAE = 7.625, RMSE = 11.92). Through an in-depth analysis of groundwater NO3-N across major urban centers, Fuyang city was identified as the most heavily contaminated locale, attributing the phenomenon to potential sources such as domestic sewage and agricultural activities (feature importance of Cl- = 78.64%). Conversely, Zhengzhou city emerged as the least polluted city, with notable influences from K+ and NO2 - (feature importance = 52.06% and 18.41%), indicative of a prevailing reducing environment compared to other cities. In summation, this study explores a methodology for amalgamating diverse environmental variables in the investigation of groundwater contamination. Such insights hold profound implications for the effective management and mitigation of nitrate contamination in the Shaying River Basin, offering a demonstration for similar endeavors in analogous regions. PRACTITIONER POINTS: Six machine learning models were utilized to simulate the nitrate contamination. XGB model for groundwater nitrate pollution prediction outperformed other models. Relative importance of environmental variables was identified using the XGB model. Impact of main environmental variables on groundwater nitrate was discussed.

Mapping the spatial transferability of knowledge-guided machine learning: Application to the prediction of drain flow fraction

Machine learning (ML) methods continue to gain traction in hydrological sciences for predicting variables at large scales. Yet, the spatial transferability of these ML methods remains a critical yet underexamined aspect. We present a metamodel approach to obtain large-scale estimates of drain fraction at 10 m spatial resolution, using a ML algorithm (Gradient Boost Decision Tree). Our variable of interest is drain, as artificial drainage of agricultural land is widespread in areas with high groundwater tables. Drainage has significant effects on the hydrological cycle, and impacts groundwater recharge, streamflow partitioning and nutrient transport. Drain flow is controlled by small-scale variations in topography, geology and groundwater depth, which presents challenges to its estimation at large scale. Drain fraction is the average ratio between drain flow and precipitation. The metamodel combines covariates based on topography, land use and geology with simulated drain fraction from 45 field-scalephysically-based hydrological models of Danish drain catchments. The 45 models were jointly calibrated against timeseries of drain flow observations. The metamodel was used to upscale predictions of drain fractions for the entirety of Danish agricultural land. This involved considerable extrapolation beyond the 45 drain catchments used for training, calling for an assessment of spatial transferability. To map transferability of the model, and distinguish areas where metamodel results are reliable or not, we used the concept of area of applicability (AOA). The AOA is determined from the similarity of covariate space covered by the training data compared to each prediction point, assuming a correlation between model performance and covariate similarity. AOA mapping showed 71 % of Denmark's agricultural land falling within the AOA of the metamodel. The study presents a stepwise methodology to obtain national-scale results using a ML model trained on local-scale numeric models and an evaluation of its spatial transferability, highly relevant for decision-support purposes.

Quantifying the sources and health risks of groundwater nitrate via dual NO isotopes and Monte Carlo simulations in a developed planting-breeding area

Nitrate (NO3-) pollution in groundwater is a worldwide environmental issue, particularly in developed planting-breeding areas where there is a substantial presence of nitrogen-related sources. Here, we explored the key sources and potential health risks of NO3- in a typical planting-breeding area in the North China Plain based on dual stable isotopes and Monte Carlo simulations. The analysis results revealed that the NO3- concentration ranged from 0.02 to 44.6 mg/L, with a mean value of 7.54 mg/L, along with a significant spatial variability. Analysis by combining stable isotopes (δ15N-NO3- and δ18O-NO3-) with the Bayesian isotope mixing model (MixSIAR) revealed that soil N (60.3 %) and manure and sewage (35.9 %) contributed the most NO3- in groundwater, followed by chemical N fertilizer (2.9 %) and atmospheric N deposition (0.8 %). However, the contribution of N fertilizer may be underestimated because it has undergone a long-term applied history and have progressively accumulated in the soil, and then promoted the entry of groundwater under frequent rainfall and irrigation practices. From the probabilistic health risk assessment, a relatively low probability of exceeding the threshold (HI=1) was observed (0.2 % for adults and 2.59 % for children); nevertheless, children still face some nonnegligible risk, particularly for the oral ingestion of drinking water at high-pollution sites. Therefore, we highlight the importance of effective management of manure and sewage from breeding plants and reduction of chemical N fertilizer usage are suggested in developed agricultural areas.

Key factors affecting groundwater nitrate levels in the Yinchuan Region, Northwest China: Research using the eXtreme Gradient Boosting (XGBoost) model with the SHapley Additive exPlanations (SHAP) method

Groundwater is a vital natural resource that has been extensively used but, unfortunately, polluted by human activities, posing a potential threat to human health. Groundwater in the Yinchuan Region is contaminated with NO3-, which is harmful to the local population. This study utilized the eXtreme Gradient Boosting (XGBoost) model with the SHapley Additive exPlanations (SHAP) method to identify the key factors influencing groundwater nitrate pollution in the Yinchuan Region. The SHAP feature dependence plots revealed the intricate relationship between NO3- levels and TDS, Mn2+, TFe, and pH in complex groundwater systems. The results indicate that the high levels of groundwater NO3- are primarily caused by the combined effect of irrigation water from the Yellow River, shallow groundwater depth, unfavorable drainage, water recharge, overuse of fertilizers, and geological factors such as weathering nitrogen-bearing rocks. Hydrochemical parameters such as Mn2+, Fe2+, and pH create a strong reducing groundwater environment, resulting in lower NO3- concentrations in this region. Well depth and soil organic carbon at a depth of 80-100 cm have a negative impact on NO3- concentrations; conversely, sand in soil depths 0-20 cm and 100-150 cm and climatic factors such as precipitation have a weak but positive effect on the level of NO3- in groundwater in the region. The recommendation is to quickly and extensively implement a farming water-conservancy transformation project, reducing water-intensive crops, promoting groundwater use for irrigation in areas where soil salinization is a concern are proposed. This research could provide local agencies with a scientific foundation for sustainable management of farming and groundwater in the Yinchuan Region, ultimately benefiting the entire Yinchuan Plain.

The private well water climate impact index: Characterization of community-level climate-related hazards and vulnerability in the continental United States

BACKGROUND

Private wells use groundwater as their source and their drinking water quality is unregulated in the United States at the federal level. Due to the lack of water quality regulations, those reliant on private wells have the responsibility of ensuring that the water is safe to drink. Where extreme weather is projected to increase with climate change, contamination due to climate-related hazards adds further layers of complexity for those relying on private wells. We sought to characterize community-level climate-related hazards and vulnerability for persons dependent on private wells in the continental United States (CONUS). Additional objectives of this work were to quantify the burden to private well water communities by climate region and demographic group.

METHODS

Grounded in the latest climate change framework and private well water literature, we created the Private Well Water Climate Impact Index (PWWCII). We searched the literature and identified nationally consistent, publicly available, sub-county data to build Overall, Drought, Flood, and Wildfire PWWCIIs at the national and state scales. We adapted the technical construction of this relative index from the California Communities Environmental Health Screening Tool (CalEnviroScreen 4.0).

RESULTS

The distribution of climate-related impact census tracts varied across CONUS by nationally-normed PWWCII type. Compared to the Southeast where the majority of the 2010 estimated U.S. private well water population lived, the estimated persons dependent upon private well water living in the West had an increased odds of living in higher impact census tracts for the Overall, Drought, and Wildfire PWWCIIs across CONUS. Compared to non-Hispanic White persons, non-Hispanic American Indian and Alaska Native (AI/AN) persons had an increased odds of living in higher impact census tracts for all four PWWCII types across CONUS.

CONCLUSIONS

The PWWCII fills a gap as it provides a baseline understanding of potential climate-related impacts to communities reliant on private well water across CONUS.

Prioritizing US Geological Survey science on salinization and salinity in candidate and selected priority river basins

The US Geological Survey (USGS) is selecting and prioritizing basins, known as Integrated Water Science basins, for monitoring and intensive study. Previous efforts to aid in this selection process include a scientifically defensible and quantitative assessment of basins facing human-caused water resource challenges (Van Metre et al. in Environmental Monitoring and Assessment, 192(7), 458 2020). In the present work, we explore this ranking process based on water quality considerations, specifically salinity and salinization. We selected top candidate basins to study salinity and salinization issues in 18 hydrologic regions that include 163 candidate basins. Our prioritization is based on quantitative assessment of sources of salinity, drivers of change, and receptors that must respond to those sources and drivers. Source terms represented in the prioritization include geology, depth to brackish groundwater, stream conductivity, chloride in precipitation, urban and agricultural land use, application of road salt as a deicer, and irrigation. Drivers represented in prioritization include changes in chemical weathering as a result of changes in rainwater chemistry. Receptors include measures of water stress, measurements of stream ecological health, and socioeconomic factors. In addition, we present research activities for the USGS on salinity and salinization that can be pursued in these basins including assessment of sources, pathways, and loadings; predicting and understanding changes in sources, peaks, and trends; understanding the components of salinity and mobilization of contaminants; understanding the relationship between salinization and changing ecosystems; and developing knowledge on the causes and distribution of groundwater salinity, brackish water resources, and challenges related to desalination.

Seasonal dynamics of dissolved inorganic nitrogen in groundwater: Tracing environmental controls and land use impact

High levels of dissolved inorganic nitrogen (DIN) in groundwater pose challenges for regions like northern Anhui Province, China, where groundwater is a crucial domestic resource. This study utilized modern geostatistics to explore the spatial and temporal dynamics of DIN in groundwater. Significant seasonal influences on DIN concentrations were identified: ammonium peaks during wet season driven by agricultural activities, while nitrate peaks during the dry season primarily influenced by municipal inputs. This study established a Bayesian Maximum Entropy - Random Forest (BME-RF) model based on Land Use/Land Cover data to infer the spatio-temporal performance of DIN, achieving an interpretation rate above 90 %. It also highlighted the role of hydrogeological conditions and aquifer types in the evolution of DIN. By employing a DIN environmental interaction model, it further analyzed the eco-hydrological drivers and seasonal trends affecting DIN variability, enhancing the understanding of groundwater nitrogen dynamics and their link to environmental factors with low consumption. SYNOPSIS: This study reveals seasonal shifts in groundwater DIN, links them to human activity, and uses the BME model to guide targeted nitrogen fluctuation.

Spatial distribution and hydrogeochemical processes of high iodine groundwater in the Hetao Basin, China

To understand the genesis and spatial distribution of high iodine groundwater in the Hetao Basin, 540 groundwater samples were analyzed for the chemistry and isotope. Total iodine concentrations in groundwater range from 1.32 to 2897 μg/L, with a mean value of 159.2 μg/L. The groundwater environment was mainly characterized by the weakly alkaline and reducing conditions, with the iodide as the main species of groundwater iodine. High iodine groundwater (I > 100 μg/L) was mainly distributed in shallow aquifers (< 30 m) of Hangjinhouqi near the Langshan Mountain and the discharge areas along the main drainage channels. The δ18O and δ2H values ranged from -12.09 ‰ to -3.99 ‰ and - 91.58 ‰ to -52.80 ‰, respectively, and the correlation between groundwater iodine and isotopes indicates the dominant role of evapotranspiration in the enrichment of iodine in the shallow groundwater with depth <30 m. It was further evidenced by the correlation between groundwater iodine and Cl/Br molar ratio, and significant contributions of climate factors identified from the random forest and XGBoost. Moreover, irrigation practices contribute to high iodine levels, with surface water used for irrigation containing up to 537.8 μg/L of iodine, which can be introduced into shallow aquifer directly. The iodine in irrigation water can be retained in the soil or shallow sediment, and later leach into groundwater under favorable conditions.

Predictions of groundwater PFAS occurrence at drinking water supply depths in the United States

Per- and polyfluoroalkyl substances (PFAS), known colloquially as "forever chemicals," have been associated with adverse human health effects and have contaminated drinking water supplies across the United States owing to their long-term and widespread use. People in the United States may unknowingly be drinking water that contains PFAS because of a lack of systematic analysis, particularly in domestic water supplies. We present an extreme gradient-boosting model for predicting the occurrence of PFAS in groundwater at the depths of drinking water supply for the conterminous United States. Our model results indicate that 71 million to 95 million people in the conterminous United States potentially rely on groundwater with detectable concentrations of PFAS for their drinking water supplies before any treatment.

Predicting flood stages in watersheds with different scales using hourly rainfall dataset: A high-volume rainfall features empowered machine learning approach

Accurate prediction of instantaneous high lake water levels and flood flows (flood stages) from micro-catchments to big river basins are critical for flood forecasting. Lake Carl Blackwell, a small-watershed reservoir in the south-central USA, served as a primary case study due to its rich historical dataset. Bearing knowledge that both current and previous rainfall contributes to the reservoirs' water body, a series of hourly rainfall features were created to maximize predicting power, which include total rainfall amounts in the current hour, the past 2 h, 3 h, …, 600 h in addition to previous-day lake levels. Notedly, the rainfall features are the accumulated rainfall amounts from present to previous hours rather than the rainfall amount in any specific hour. Random Forest Regression (RFR) was used to score the features' importance and predict the flood stages along with Neural Network - Multi-layer Perceptron Regression (NN-MLP), Support Vector Regression (SVR), Extreme Gradient Boosting (XGBoost), and the ordinary multi-variant linear regression (MLR) together with dimension reduced linear models of Principal Component Regression (PCR) and Partial Least Square Regression (PLSR). The prediction accuracy for the lake flood stages can be as high as 0.95 in R2, 0.11 ft. in mean absolute error (MAE), and 0.21 ft. in root mean square error (RMSE) for the testing dataset by the RFR (NN-MLP performed equally well), with small accuracy decreases by the other two non-linear algorithms of XGBoost and SVR. The linear regressions with dimension reductions had the lowest accuracy. Furthermore, our approach demonstrated high accuracy and broad applicability for surface runoff and streamflow predictions across three different-sized watersheds from micro-catchment to big river basins in the region, with increases of predicting power from earlier rainfall for larger watersheds and vice versa.

Statistical Mapping of PFOA and PFOS in Groundwater throughout the Contiguous United States

Per-and polyfluoroalkyl substances (PFAS) are synthetic chemicals that are increasingly being detected in groundwater. The negative health consequences associated with human exposure to PFAS make it essential to quantify the distribution of PFAS in groundwater systems. Mapping PFAS distributions is particularly challenging because a national patchwork of testing and reporting requirements has resulted in sparse and spatially biased data. In this analysis, an inhomogeneous Poisson process (IPP) modeling approach is adopted from ecological statistics to continuously map PFAS distributions in groundwater across the contiguous United States. The model is trained on a unique data set of 8910 PFAS groundwater measurements, using combined concentrations of two PFAS analytes. The IPP model predictions are compared with results from random forest models to highlight the robustness of this statistical modeling approach on sparse data sets. This analysis provides a new approach to not only map PFAS contamination in groundwater but also prioritize future sampling efforts.

Advancing groundwater quality predictions: Machine learning challenges and solutions

Machine learning (ML) is revolutionizing groundwater quality research by enhancing predictive accuracy and management strategies for contamination. This comprehensive review explores the evolution of ML technologies and their integration into environmental science, assessing 230 papers to understand the advancements and challenges in groundwater quality research. It reveals that a substantial portion of the research neglects critical preprocessing steps, crucial for model accuracy, with 83 % of the studies overlooking this phase. Furthermore, while model optimization is more commonly addressed, being implemented in 65 % of the papers, there is a noticeable gap in model interpretability, with only 15 % of the research providing explanations for model outcomes. Comparative evaluation of ML algorithms and careful selection of evaluation metrics are deemed essential for determining model fitness and reliability. The review underscores the need for interdisciplinary collaboration, methodological rigor, and continuous innovation to advance ML in groundwater management. By addressing these challenges and implementing solutions, the full potential of ML can be harnessed to tackle complex environmental issues and ensure sustainable groundwater management. This comprehensive and critical review paper can serve as a guiding framework to establish minimum standards for developing ML in groundwater quality studies.

Identifying the spatial pattern and driving factors of nitrate in groundwater using a novel framework of interpretable stacking ensemble learning

Groundwater nitrate contamination poses a potential threat to human health and environmental safety globally. This study proposes an interpretable stacking ensemble learning (SEL) framework for enhancing and interpreting groundwater nitrate spatial predictions by integrating the two-level heterogeneous SEL model and SHapley Additive exPlanations (SHAP). In the SEL model, five commonly used machine learning models were utilized as base models (gradient boosting decision tree, extreme gradient boosting, random forest, extremely randomized trees, and k-nearest neighbor), whose outputs were taken as input data for the meta-model. When applied to the agricultural intensive area, the Eden Valley in the UK, the SEL model outperformed the individual models in predictive performance and generalization ability. It reveals a mean groundwater nitrate level of 2.22 mg/L-N, with 2.46% of sandstone aquifers exceeding the drinking standard of 11.3 mg/L-N. Alarmingly, 8.74% of areas with high groundwater nitrate remain outside the designated nitrate vulnerable zones. Moreover, SHAP identified that transmissivity, baseflow index, hydraulic conductivity, the percentage of arable land, and the C:N ratio in the soil were the top five key driving factors of groundwater nitrate. With nitrate threatening groundwater globally, this study presents a high-accuracy, interpretable, and flexible modeling framework that enhances our understanding of the mechanisms behind groundwater nitrate contamination. It implies that the interpretable SEL framework has great promise for providing valuable evidence for environmental management, water resource protection, and sustainable development, particularly in the data-scarce area.

Groundwater quality in high-sulfur coal mining region of India: Spatial distribution, source control, and health risk assessment

The groundwater quality in the vicinity of the Makum coalfield, renowned for its high-sulfur coal deposits, was investigated. The oxidation of sulfur in the coal generates acid mine drainage (AMD), a global environmental challenge that contaminates natural resources. The region's high sulfur coal content intensifies AMD formation, necessitating a comprehensive assessment of its impact on human health and the environment. This study analyzes the water quality parameters such as pH, EC, TDS, Na+, Ca+2, Mg+2, K+, HCO3-, SO4-2, F-, Cl -, and NO3- in groundwater, findings concerning low pH levels (5.8) and fluoride concentration (0.15 mg/L) compared to standards. Groundwater chemistry was analyzed to identify the sources controlling water composition through Gibbs diagrams, Piper diagrams, and saturation indices. The Gibbs diagram shows that rock weathering is the crucial factor controlling groundwater chemistry, while the Piper diagram indicates Ca-Cl as the Principal water type. Additionally, an in-depth analysis of groundwater chemistry reveals that carbonate dissolution primarily occurs due to minerals like calcite, dolomite, and gypsum, findings supported by saturation indices. The present study yielded an average water quality index of 40.19, indicating excellent to good water quality in 51 out of 52 samples analyzed. The average hazard index values for adults and children were 0.60 and 0.58, respectively, indicating that 49 of 52 samples pose negative non-carcinogenic risks associated with nitrate and fluoride contamination. The irrigation indices, graphical representations such as the Wilcox and Doneen classification, and the USSL diagram elucidate the suitability for irrigation purposes. Moreover, the Principal Component Analysis identified the sources of ions as originating from geogenic processes and mining activities. The study stresses environmental assessments, health risk management, and sustainable practices for groundwater in high-sulfur coal mining areas.

Improving Private Well Testing Programs: Experimental Evidence from Iowa

Approximately 23 million U.S. households rely on private wells for drinking water. This study first summarizes drinking water behaviors and perceptions from a large-scale survey of households that rely on private wells in Iowa. Few households test as frequently as recommended by public health experts. Around 40% of households do not regularly test, treat, or avoid their drinking water, suggesting pollution exposure may be widespread among this population. Next, we utilize a randomized control trial to study how nitrate test strips and information about a free, comprehensive water quality testing program influence households' behaviors and perceptions. The intervention significantly increased testing, including high-quality follow-up testing, but had limited statistically detectable impacts on other behaviors and perceptions. Households' willingness to pay for nitrate test kits and testing information exceeds program costs, suggesting that the intervention was welfare-enhancing.

Assessment of spatiotemporal risks for nationwide groundwater nitrate contamination

National assessments of groundwater contamination risks are crucial for sustaining high-quality groundwater supplies. However, traditional methods often treat groundwater contamination risk as a steady-state indicator without considering spatiotemporal variation in risk, both geographically and over time, caused by anthropogenic and climatic factors. In this work, XGBoost, a tree-based algorithm, was applied to comprehensively analyze the drivers of groundwater contamination from nitrate, using data on 13 physical features (as used by the index-based ranking method DRASTIC) and 30 anthropogenic features from 1985 to 2010 in the contiguous United States (CONUS). The results indicate that physical features controlling the transport processes, particularly those affecting contaminant travel time from land surface to groundwater (depth to water table and transmissivity), were the dominant factors for nitrate contamination in groundwater. This was followed by features representing the potential nitrogen loading. Positive correlations between most features and the nitrogen loading time (year) were found, suggesting their growing influence on contamination risk. Based on the drivers identified for nitrate concentrations exceeding 10 mg/L in groundwater and their varying temporal contributions, this study proposes a reformulated index-based method for contamination risk assessment. With this method, an overall accuracy of around 70 % was achieved based on the validation data set. The predicted high-risk areas are mainly intensive irrigation regions, such as the High Plains, northern Midwest, and Central Valley. This new approach contributes to a more accurate and effective assessment of the contamination risks of groundwater on a regional and national scale under temporally varying environmental conditions.

Electrocatalysts for Inorganic and Organic Waste Nitrogen Conversion

Anthropogenic activities have disrupted the natural nitrogen cycle, increasing the level of nitrogen contaminants in water. Nitrogen contaminants are harmful to humans and the environment. This motivates research on advanced and decarbonized treatment technologies that are capable of removing or valorizing nitrogen waste found in water. In this context, the electrocatalytic conversion of inorganic- and organic-based nitrogen compounds has emerged as an important approach that is capable of upconverting waste nitrogen into valuable compounds. This approach differs from state-of-the-art wastewater treatment, which primarily converts inorganic nitrogen to dinitrogen, and organic nitrogen is sent to landfills. Here, we review recent efforts related to electrocatalytic conversion of inorganic- and organic-based nitrogen waste. Specifically, we detail the role that electrocatalyst design (alloys, defects, morphology, and faceting) plays in the promotion of high-activity and high-selectivity electrocatalysts. We also discuss the impact of wastewater constituents. Finally, we discuss the critical product analyses required to ensure that the reported performance is accurate.

Machine Learning Integrating Protein Structure, Sequence, and Dynamics to Predict the Enzyme Activity of Bovine Enterokinase Variants

Despite recent advances in computational protein science, the dynamic behavior of proteins, which directly governs their biological activity, cannot be gleaned from sequence information alone. To overcome this challenge, we propose a framework that integrates the peptide sequence, protein structure, and protein dynamics descriptors into machine learning algorithms to enhance their predictive capabilities and achieve improved prediction of the protein variant function. The resulting machine learning pipeline integrates traditional sequence and structure information with molecular dynamics simulation data to predict the effects of multiple point mutations on the fold improvement of the activity of bovine enterokinase variants. This study highlights how the combination of structural and dynamic data can provide predictive insights into protein functionality and address protein engineering challenges in industrial contexts.

Mapping specific groundwater nitrate concentrations from spatial data using machine learning: A case study of chongqing, China

Groundwater resources is not only important essential water resources but also imperative connectors within the intricate framework of the ecological environment. High nitrate concentrations in groundwater can exerting adverse impacts on human health. It is imperative to accurately delineate the distribution characteristics of groundwater nitrate concentrations. Four different machine learning models (Gradient Boosting Regression (GB), Random Forest Regression (RF), Extreme Gradient Boosting Regression (XG) and Adaptive Boosting Regression (AD)) which combine spatial environmental data and different radius contributing area was developed to predict the distribution of nitrate concentration in groundwater. The models use 595 groundwater samples and included topography, remote sensing, hydrogeological and hydrological, climate, nitrate input, and socio-economic predictor. Gradient Boosting Regression model outperforms the other models (R2 = 0.627, MAE = 0.529, RMSE = 0.705, PICP = 0.924 for test dataset) under 500 m radius contributing area. A high-resolution (1 km) groundwater nitrate concentration distribution map reveal in the majority of the study area, groundwater nitrate concentrations are below 1 mg/L and high nitrate concentration (>10 mg/L) proportion in southeast, northeast and central main urban area karst valley regions is 1.89%, 0.91%, and 0.38% respectively. In study area, hydrogeological conditions, soil parameters, nitrogen input factors, and percentage of arable land are among the most influential explanatory factors. This work, serving as the inaugural application of utilizing effective spatial methods for predicting groundwater nitrate concentrations in Chongqing city, furnish decision-making support for the prevention and control of groundwater pollution, particularly in areas primarily dependent on groundwater for water supply and holds profound significance as a milestone achievement.

Reliable water quality prediction and parametric analysis using explainable AI models

The consumption of water constitutes the physical health of most of the living species and hence management of its purity and quality is extremely essential as contaminated water has to potential to create adverse health and environmental consequences. This creates the dire necessity to measure, control and monitor the quality of water. The primary contaminant present in water is Total Dissolved Solids (TDS), which is hard to filter out. There are various substances apart from mere solids such as potassium, sodium, chlorides, lead, nitrate, cadmium, arsenic and other pollutants. The proposed work aims to provide the automation of water quality estimation through Artificial Intelligence and uses Explainable Artificial Intelligence (XAI) for the explanation of the most significant parameters contributing towards the potability of water and the estimation of the impurities. XAI has the transparency and justifiability as a white-box model since the Machine Learning (ML) model is black-box and unable to describe the reasoning behind the ML classification. The proposed work uses various ML models such as Logistic Regression, Support Vector Machine (SVM), Gaussian Naive Bayes, Decision Tree (DT) and Random Forest (RF) to classify whether the water is drinkable. The various representations of XAI such as force plot, test patch, summary plot, dependency plot and decision plot generated in SHAPELY explainer explain the significant features, prediction score, feature importance and justification behind the water quality estimation. The RF classifier is selected for the explanation and yields optimum Accuracy and F1-Score of 0.9999, with Precision and Re-call of 0.9997 and 0.998 respectively. Thus, the work is an exploratory analysis of the estimation and management of water quality with indicators associated with their significance. This work is an emerging research at present with a vision of addressing the water quality for the future as well.

Revealing the drivers and genesis of NO3-N pollution classification in shallow groundwater of the Shaying River Basin by explainable machine learning and pathway analysis method

Nitrate (NO3-N), as one of the ubiquitous contaminants in groundwater worldwide, has posed a serious threat to public health and the ecological environment. Despite extensive research on its genesis, little is known about the differences in the genesis of NO3-N pollution across different concentrations. Herein, a study of NO3-N pollution concentration classification was conducted using the Shaying River Basin as a typical area, followed by examining the genesis differences across different pollution classifications. Results demonstrated that three classifications (0-9.98 mg/L, 10.14-27.44 mg/L, and 28.34-136.30 mg/L) were effectively identified for NO3-N pollution using Jenks natural breaks method. Random forest exhibited superior performance in describing NO3-N pollution and was thereby affirmed as the optimal explanatory method. With this method coupling SEMs, the genesis of different NO3-N pollution classifications was proven to be significantly different. Specifically, strongly reducing conditions represented by Mn2+, Eh, and NO2-N played a dominant role in causing residual NO3-N at low levels. Manure and sewage (represented by Cl-) leaching into groundwater through precipitation is mainly responsible for NO3-N in the 10-30 mg/L classification, with a cumulative contribution rate exceeding 80 %. NO3-N concentrations >30 mg/L are primarily caused by the anthropogenic loads stemming from manure, sewage, and agricultural fertilization (represented by Cl- and K+) infiltrating under precipitation in vulnerable hydrogeological conditions. Pathway analysis based on standardized effect and significance further confirmed the rationality and reliability of the above results. The findings will provide more accurate information for policymakers in groundwater resource management to implement effective strategies to mitigate NO3-N pollution.

Predicting Redox Conditions in Groundwater at a National Scale Using Random Forest Classification

Redox conditions in groundwater may markedly affect the fate and transport of nutrients, volatile organic compounds, and trace metals, with significant implications for human health. While many local assessments of redox conditions have been made, the spatial variability of redox reaction rates makes the determination of redox conditions at regional or national scales problematic. In this study, redox conditions in groundwater were predicted for the contiguous United States using random forest classification by relating measured water quality data from over 30,000 wells to natural and anthropogenic factors. The model correctly predicted the oxic/suboxic classification for 78 and 79% of the samples in the out-of-bag and hold-out data sets, respectively. Variables describing geology, hydrology, soil properties, and hydrologic position were among the most important factors affecting the likelihood of oxic conditions in groundwater. Important model variables tended to relate to aquifer recharge, groundwater travel time, or prevalence of electron donors, which are key drivers of redox conditions in groundwater. Partial dependence plots suggested that the likelihood of oxic conditions in groundwater decreased sharply as streams were approached and gradually as the depth below the water table increased. The probability of oxic groundwater increased as base flow index values increased, likely due to the prevalence of well-drained soils and geologic materials in high base flow index areas. The likelihood of oxic conditions increased as topographic wetness index (TWI) values decreased. High topographic wetness index values occur in areas with a propensity for standing water and overland flow, conditions that limit the delivery of dissolved oxygen to groundwater by recharge; higher TWI values also tend to occur in discharge areas, which may contain groundwater with long travel times. A second model was developed to predict the probability of elevated manganese (Mn) concentrations in groundwater (i.e., ≥50 μg/L). The Mn model relied on many of the same variables as the oxic/suboxic model and may be used to identify areas where Mn-reducing conditions occur and where there is an increased risk to domestic water supplies due to high Mn concentrations. Model predictions of redox conditions in groundwater produced in this study may help identify regions of the country with elevated groundwater vulnerability and stream vulnerability to groundwater-derived contaminants.

Deep learning for water quality

Understanding and predicting the quality of inland waters are challenging, particularly in the context of intensifying climate extremes expected in the future. These challenges arise partly due to complex processes that regulate water quality, and arduous and expensive data collection that exacerbate the issue of data scarcity. Traditional process-based and statistical models often fall short in predicting water quality. In this Review, we posit that deep learning represents an underutilized yet promising approach that can unravel intricate structures and relationships in high-dimensional data. We demonstrate that deep learning methods can help address data scarcity by filling temporal and spatial gaps and aid in formulating and testing hypotheses via identifying influential drivers of water quality. This Review highlights the strengths and limitations of deep learning methods relative to traditional approaches, and underscores its potential as an emerging and indispensable approach in overcoming challenges and discovering new knowledge in water-quality sciences.

Ingested nitrate and nitrite and end-stage renal disease in licensed pesticide applicators and spouses in the Agricultural Health Study

BACKGROUND

Nitrate and nitrite ingestion has been linked to kidney cancer, possibly via the endogenous formation of carcinogenic N-nitroso compounds. These exposures might also contribute to end-stage renal disease (ESRD).

OBJECTIVES

We investigated associations of drinking water nitrate and dietary nitrate and nitrite intakes (total and by food type) with incident ESRD in the Agricultural Health Study. We also explored modifying effects of vitamin C and heme iron intake, which may affect endogenous nitrosation.

METHODS

We performed complete case analyses among private pesticide applicators and their spouses. We obtained water nitrate estimates for participants whose primary drinking water source at enrollment (1993-1997) was public water supplies (PWS) or private wells (N = 59,632). Average nitrate concentrations were computed from historical data for PWS users and predicted from random forest models for private well users. Analysis of dietary nitrate and nitrite was restricted to the 30,177 participants who completed the NCI Dietary History Questionnaire during follow-up (1999-2003). Incident ESRD through 2018 was ascertained through linkage with the U.S. Renal Data System. We estimated adjusted hazard ratios (HRs) and 95%CI for associations of tertiles (T) of exposure with ESRD overall and explored effects in strata of vitamin C and heme iron intake.

RESULTS

We identified 469 incident ESRD cases (206 for dietary analysis). Water nitrate and total dietary nitrate/nitrite were not associated with ESRD, but increased ESRD was associated with nitrate and nitrite from processed meats. We found apparent associations between nitrite and ESRD only among participants with vitamin C

SIGNIFICANCE

ESRD incidence was associated with dietary nitrate/nitrite from processed meat among all study participants and with total dietary nitrite among participants with lower vitamin C or higher heme iron intake.

IMPACT STATEMENT

There are few well-established environmental risk factors for end-stage renal disease (ESRD), a worldwide public health challenge. Ingestion of nitrate and nitrite, which may lead to endogenous formation of carcinogenic N-nitroso compounds, has been linked to some cancers and chronic diseases. We investigated these exposures in relation to ESRD in an agricultural cohort. ESRD incidence was associated with dietary nitrate/nitrite from processed meat and with total dietary nitrite among subgroups with lower vitamin C or higher heme iron intake. This study provides preliminary evidence that points to dietary nitrite and possibly dietary nitrate intake as a potential contributor to ESRD.

Collapse

Key Words

• Chronic kidney disease
• End-stage renal disease
• Nitrate
• Nitrite
• Processed meat
• Water pollution

Collapse

MESH Headings

• Humans
• Nitrates/analysis
• Kidney Failure, Chronic/epidemiology
• Kidney Failure, Chronic/chemically induced
• Male
• Nitrites/analysis
• Nitrites/adverse effects
• Female
• Middle Aged
• Spouses/statistics & numerical data
• Adult
• Pesticides
• Occupational Exposure/adverse effects
• Occupational Exposure/analysis
• Aged
• Drinking Water/chemistry
• Drinking Water/analysis
• Incidence
• Agriculture
• Diet/statistics & numerical data
• Farmers/statistics & numerical data
• Ascorbic Acid

Collapse

Grants Collapse

Affiliation(s)

Dazhe Chen Epidemiology Branch, National Institute of Environmental Health Sciences, NIH, Research Triangle Park, NC, USA
Christine G Parks Epidemiology Branch, National Institute of Environmental Health Sciences, NIH, Research Triangle Park, NC, USA
Laura E Beane Freeman Occupational and Environmental Epidemiology Branch, Division of Cancer Epidemiology and Genetics, National Cancer Institute, NIH, Rockville, MD, USA
Jonathan N Hofmann Occupational and Environmental Epidemiology Branch, Division of Cancer Epidemiology and Genetics, National Cancer Institute, NIH, Rockville, MD, USA
Rashmi Sinha Metabolic Epidemiology Branch, Division of Cancer Epidemiology and Genetics, National Cancer Institute, NIH, Rockville, MD, USA
Jessica M Madrigal Occupational and Environmental Epidemiology Branch, Division of Cancer Epidemiology and Genetics, National Cancer Institute, NIH, Rockville, MD, USA
Mary H Ward Occupational and Environmental Epidemiology Branch, Division of Cancer Epidemiology and Genetics, National Cancer Institute, NIH, Rockville, MD, USA
Dale P Sandler Epidemiology Branch, National Institute of Environmental Health Sciences, NIH, Research Triangle Park, NC, USA.

Collapse

Collaborators Collapse

Basin-wide tracking of nitrate cycling in Yangtze River through dual isotope and machine learning

The nitrate (NO3-) input has adversely affected the water quality and ecological function in the whole basin of the Yangtze River. The protection of water sources and implementation of "great protection of Yangtze River" policy require large-scale information on water contamination. In this study, dual isotope and Bayesian mixing model were used to research the transformation and sources of nitrate. Chemical fertilizers contribute 76 % of the nitrate sources in the upstream, while chemical fertilizers were also dominant in the midstream (39 %) and downstream (39 %) of Yangtze River. In addition, nitrification process occurred in the whole basin. Four machine learning models were used to relate nitrate concentrations to explanatory variables describing influence factors to predict nitrate concentrations in the whole basin of Yangtze River. The anthropogenic and natural factors, such as rainfall, GDP and population were chosen to take as predictor variables. The eXtreme Gradient Boosting (XGBoost) model for nitrate has a better predictive performance with an R2 of 0.74. The predictive models of nitrate concentrations will help identify the nitrate distribution and transport in the whole Yangtze River basin. Overall, this study represents the first basin-wide data-driven assessment of the nitrate cycling in the Yangtze River basin.

Prioritizing river basins for nutrient studies

Increases in fluxes of nitrogen (N) and phosphorus (P) in the environment have led to negative impacts affecting drinking water, eutrophication, harmful algal blooms, climate change, and biodiversity loss. Because of the importance, scale, and complexity of these issues, it may be useful to consider methods for prioritizing nutrient research in representative drainage basins within a regional or national context. Two systematic, quantitative approaches were developed to (1) identify basins that geospatial data suggest are most impacted by nutrients and (2) identify basins that have the most variability in factors affecting nutrient sources and transport in order to prioritize basins for studies that seek to understand the key drivers of nutrient impacts. The "impact" approach relied on geospatial variables representing surface-water and groundwater nutrient concentrations, sources of N and P, and potential impacts on receptors (i.e., ecosystems and human health). The "variability" approach relied on geospatial variables representing surface-water nutrient concentrations, factors affecting sources and transport of nutrients, model accuracy, and potential receptor impacts. One hundred and sixty-three drainage basins throughout the contiguous United States were ranked nationally and within 18 hydrologic regions. Nationally, the top-ranked basins from the impact approach were concentrated in the Midwest, while those from the variability approach were dispersed across the nation. Regionally, the top-ranked basin selected by the two approaches differed in 15 of the 18 regions, with top-ranked basins selected by the variability approach having lower minimum concentrations and larger ranges in concentrations than top-ranked basins selected by the impact approach. The highest ranked basins identified using the variability approach may have advantages for exploring how landscape factors affect surface-water quality and how surface-water quality may affect ecosystems. In contrast, the impact approach prioritized basins in terms of human development and nutrient concentrations in both surface water and groundwater, thereby targeting areas where actions to reduce nutrient concentrations could have the largest effect on improving water availability and reducing ecosystem impacts.

On the challenges of global entity-aware deep learning models for groundwater level prediction

Abstract. The application of machine learning (ML) including deep learning models in hydrogeology to model and predict groundwater level in monitoring wells has gained some traction in recent years. Currently, the dominant model class is the so-called single-well model, where one model is trained for each well separately. However, recent developments in neighbouring disciplines including hydrology (rainfall–runoff modelling) have shown that global models, being able to incorporate data of several wells, may have advantages. These models are often called “entity-aware models“, as they usually rely on static data to differentiate the entities, i.e. groundwater wells in hydrogeology or catchments in surface hydrology. We test two kinds of static information to characterize the groundwater wells in a global, entity-aware deep learning model set-up: first, environmental features that are continuously available and thus theoretically enable spatial generalization (regionalization), and second, time-series features that are derived from the past time series at the respective well. Moreover, we test random integer features as entity information for comparison. We use a published dataset of 108 groundwater wells in Germany, and evaluate the performance of the models in terms of Nash–Sutcliffe efficiency (NSE) in an in-sample and an out-of-sample setting, representing temporal and spatial generalization. Our results show that entity-aware models work well with a mean performance of NSE >0.8 in an in-sample setting, thus being comparable to, or even outperforming, single-well models. However, they do not generalize well spatially in an out-of-sample setting (mean NSE <0.7, i.e. lower than a global model without entity information). Strikingly, all model variants, regardless of the type of static features used, basically perform equally well both in- and out-of-sample. The conclusion is that the model in fact does not show entity awareness, but uses static features merely as unique identifiers, raising the research question of how to properly establish entity awareness in deep learning models. Potential future avenues lie in bigger datasets, as the relatively small number of wells in the dataset might not be enough to take full advantage of global models. Also, more research is needed to find meaningful static features for ML in hydrogeology.

Estimating Lithium Concentrations in Groundwater Used as Drinking Water for the Conterminous United States

Lithium (Li) concentrations in drinking-water supplies are not regulated in the United States; however, Li is included in the 2022 U.S. Environmental Protection Agency list of unregulated contaminants for monitoring by public water systems. Li is used pharmaceutically to treat bipolar disorder, and studies have linked its occurrence in drinking water to human-health outcomes. An extreme gradient boosting model was developed to estimate geogenic Li in drinking-water supply wells throughout the conterminous United States. The model was trained using Li measurements from ∼13,500 wells and predictor variables related to its natural occurrence in groundwater. The model predicts the probability of Li in four concentration classifications, ≤4 μg/L, >4 to ≤10 μg/L, >10 to ≤30 μg/L, and >30 μg/L. Model predictions were evaluated using wells held out from model training and with new data and have an accuracy of 47-65%. Important predictor variables include average annual precipitation, well depth, and soil geochemistry. Model predictions were mapped at a spatial resolution of 1 km2 and represent well depths associated with public- and private-supply wells. This model was developed by hydrologists and public-health researchers to estimate Li exposure from drinking water and compare to national-scale human-health data for a better understanding of dose-response to low (<30 μg/L) concentrations of Li.

US drinking water quality: exposure risk profiles for seven legacy and emerging contaminants

BACKGROUND

Advances in drinking water infrastructure and treatment throughout the 20th and early 21st century dramatically improved water reliability and quality in the United States (US) and other parts of the world. However, numerous chemical contaminants from a range of anthropogenic and natural sources continue to pose chronic health concerns, even in countries with established drinking water regulations, such as the US.

OBJECTIVE/METHODS

In this review, we summarize exposure risk profiles and health effects for seven legacy and emerging drinking water contaminants or contaminant groups: arsenic, disinfection by-products, fracking-related substances, lead, nitrate, per- and polyfluorinated alkyl substances (PFAS) and uranium. We begin with an overview of US public water systems, and US and global drinking water regulation. We end with a summary of cross-cutting challenges that burden US drinking water systems: aging and deteriorated water infrastructure, vulnerabilities for children in school and childcare facilities, climate change, disparities in access to safe and reliable drinking water, uneven enforcement of drinking water standards, inadequate health assessments, large numbers of chemicals within a class, a preponderance of small water systems, and issues facing US Indigenous communities.

RESULTS

Research and data on US drinking water contamination show that exposure profiles, health risks, and water quality reliability issues vary widely across populations, geographically and by contaminant. Factors include water source, local and regional features, aging water infrastructure, industrial or commercial activities, and social determinants. Understanding the risk profiles of different drinking water contaminants is necessary for anticipating local and general problems, ascertaining the state of drinking water resources, and developing mitigation strategies.

IMPACT STATEMENT

Drinking water contamination is widespread, even in the US. Exposure risk profiles vary by contaminant. Understanding the risk profiles of different drinking water contaminants is necessary for anticipating local and general public health problems, ascertaining the state of drinking water resources, and developing mitigation strategies.

Predicting geogenic groundwater arsenic contamination risk in floodplains using interpretable machine-learning model

Long-term exposure to geogenic arsenic (As)-contaminated groundwater poses a severe threat to public health problems. Generally, elevated As concentrations have been observed with high amounts of ammonium in groundwater of floodplains. An extreme gradient boosting algorithm was conducted to develop a probability model based on hydrogeochemical data, which predicted the occurrence rates of groundwater As on a regional scale. Results showed that concentrations of NH4+, Eh, K, Cl-, SO42-, and NO3- were powerful predictive variables of As exposure. The model revealed the co-enrichment of As with NH4+, suggesting that the mineralization of nitrogen-containing organic matter promoted the reduction of As-bearing iron-oxides. The predicted distribution of high-As groundwater showed high consistency with known spatial distribution of As contamination, and the model also accurately predicted As concentrations in Jiangbei Plain of China and typical As-affected floodplains of Southeast Asia. The model can serve as a low-cost and rapid virtual sensor for detecting As concentrations in private or newly drilled wells, thereby providing critical information for informed management decisions, environmental protection and public health safety.

Nitrate prediction in groundwater of data scarce regions: The futuristic fresh-water management outlook

Nitrate contamination in groundwater poses a significant threat to water quality and public health, especially in regions with limited data availability. This study addresses this challenge by employing machine learning (ML) techniques to predict nitrate (NO3--N) concentrations in Mexico's groundwater. Four ML algorithms-Extreme Gradient Boosting (XGB), Boosted Regression Trees (BRT), Random Forest (RF), and Support Vector Machines (SVM)-were executed to model NO3--N concentrations across the country. Despite data limitations, the ML models achieved robust predictive performances. XGB and BRT algorithms demonstrated superior accuracy (0.80 and 0.78, respectively). Notably, this was achieved using ∼10 times less information than previous large-scale assessments. The novelty lies in the first-ever implementation of the 'Support Points-based Split Approach' during data pre-processing. The models considered initially 68 covariates and identified 13-19 significant predictors of NO3--N concentration spanning from climate, geomorphology, soil, hydrogeology, and human factors. Rainfall, elevation, and slope emerged as key predictors. A validation incorporated nationwide waste disposal sites, yielding an encouraging correlation. Spatial risk mapping unveiled significant pollution hotspots across Mexico. Regions with elevated NO3--N concentrations (>10 mg/L) were identified, particularly in the north-central and northeast parts of the country, associated with agricultural and industrial activities. Approximately 21 million people, accounting for 10 % of Mexico's population, are potentially exposed to elevated NO3--N levels in groundwater. Moreover, the NO3--N hotspots align with reported NO3--N health implications such as gastric and colorectal cancer. This study not only demonstrates the potential of ML in data-scarce regions but also offers actionable insights for policy and management strategies. Our research underscores the urgency of implementing sustainable agricultural practices and comprehensive domestic waste management measures to mitigate NO3--N contamination. Moreover, it advocates for the establishment of effective policies based on real-time monitoring and collaboration among stakeholders.

Human and natural impacts on the U.S. freshwater salinization and alkalinization: A machine learning approach

Ongoing salinization and alkalinization in U.S. rivers have been attributed to inputs of road salt and effects of human-accelerated weathering in previous studies. Salinization poses a severe threat to human and ecosystem health, while human derived alkalinization implies increasing uncertainty in the dynamics of terrestrial sequestration of atmospheric carbon dioxide. A mechanistic understanding of whether and how human activities accelerate weathering and contribute to the geochemical changes in U.S. rivers is lacking. To address this uncertainty, we compiled dissolved sodium (salinity proxy) and alkalinity values along with 32 watershed properties ranging from hydrology, climate, geomorphology, geology, soil chemistry, land use, and land cover for 226 river monitoring sites across the coterminous U.S. Using these data, we built two machine-learning models to predict monthly-aggregated sodium and alkalinity fluxes at these sites. The sodium-prediction model detected human activities (represented by population density and impervious surface area) as major contributors to the salinity of U.S. rivers. In contrast, the alkalinity-prediction model identified natural processes as predominantly contributing to variation in riverine alkalinity flux, including runoff, carbonate sediment or siliciclastic sediment, soil pH and soil moisture. Unlike prior studies, our analysis suggests that the alkalinization in U.S. rivers is largely governed by local climatic and hydrogeological conditions.

Geostatistical estimates of groundwater nitrate-nitrogen concentrations with spatial auxiliary information on DRASTIC-LU-based aquifer contamination vulnerability

Groundwater nitrate-nitrogen contamination typically involves several natural and anthropogenic factors, including those related to hydrology, hydrogeology, topography, and land use (LU). DRASTIC-LU-based aquifer contamination vulnerability could be used to characterize the pollution potentials of groundwater nitrate-nitrogen and to determine groundwater protection zones. This study used regression kriging (RK) with environmental auxiliary information on DRASTIC-LU-based aquifer contamination vulnerability to investigate groundwater nitrate-nitrogen pollution in the Pingtung Plain of Taiwan. First, the relationship between groundwater nitrate-nitrogen pollution and assessments of aquifer contamination vulnerability was determined using stepwise multivariate linear regression (MLR). Subsequently, the residuals between the nitrate-nitrogen observations and MLR predictions were estimated by kriging techniques. Finally, the groundwater nitrate-nitrogen distributions were spatially analyzed using RK, ordinary kriging (OK), and MLR. The findings indicated that the land used for orchards and the medium- and coarse-sand fractions of vadose zones were associated with groundwater nitrate-nitrogen concentrations. The fertilizer used for orchards was identified as the primary source of groundwater nitrate-nitrogen pollution. The RK estimates could be used to analyze the characteristics of the pollution source for land used for orchards and exhibited high spatial variability and accuracy after residual correction. Moreover, RK had an excellent estimate ability for extreme data compared to MLR and OK. Correctly determining groundwater nitrate-nitrogen distributions using RK was useful for administering environmental resources and preventing public health hazards.

Potential risk assessment due to groundwater quality deterioration and quantifying the major influencing factors using geographical detectors in the Gunabay watershed of Ethiopia

Groundwater quality has become deteriorated due to natural and anthropogenic activities. Poor water quality has a potential risk to human health and the environment. Therefore, the study aimed to assess the potential risk of groundwater quality contamination levels and public health risks in the Gunabay watershed. For this task, seventy-eight groundwater samples were collected from thirty-nine locations in the dry and wet seasons during 2022. The groundwater contamination index was applied to assess the overall quality of groundwater. Six major driving forces (temperature, population density, soil, land cover, recharge, and geology) and their quantitative impact of each factor on groundwater quality deterioration were demonstrated using Geodetector. The results showed that low groundwater quality was detected in urban and agricultural land. Especially nitrate contamination was highly linked to groundwater quality deterioration and public health risks, and a medium contamination level was observed in the area. This indicates that the inappropriate application of fertilizer on agricultural land and wastewater from urban areas has a great impact on shallow aquifers in the study area. Furthermore, the major influencing factors are ranked as soil type (0.33-0.31) > recharge (0.17-0.15) > temperature (0.13-0.08) > population density (0.1-0.08) > land cover types (0.07-0.04) > lithology (0.05-0.04). The interaction detector revealed that the interaction between soil ∩ recharge, soil ∩ temperature, and soil ∩ land cover, temperature ∩ recharge is more influential to deteriorate groundwater quality in both seasons. Identification and quantification of the major influencing factors may provide new insight into groundwater resource management.

A supervised machine learning approach to discriminate the effect of carcass leachate on shallow groundwater quality around on-farm livestock mortality burial sites

The evaluation of leachate leakage at livestock mortality burial sites is challenging, particularly when groundwater is previously contaminated by agro-livestock farming. Supervised machine learning was applied to discriminate the impacts of carcass leachate from pervasive groundwater contamination in the following order: data labeling, feature selection, synthetic data generation, and classification. Physicochemical data of 359 water samples were collected from burial pits (LC), monitoring wells near pits (MW), pre-existing shallow household wells (HW), and background wells with pervasive contamination (BG). A linear classification model was built using two representative groups (LC and BG) affected by different pollution sources as labeled data. A classifier was then applied to assess the impact of leachate leakage in MW and HW. As a result, leachate impacts were observed in 40% of MW samples, which indicates improper construction and management of some burial pits. Leachate impacts were also detected in six HW samples, up to 120 m downgradient, within one year. The quantitative decision-making tool to diagnose groundwater contamination with leachate leakage can contribute to ensuring timely responses to leakage. The proposed machine learning approach can also be used to improve the environmental impact assessment of water pollution by improper disposal of organic waste.

Hotspot and accumulated hotspot analysis for assessment of groundwater quality and pollution indices using GIS in the arid region of Iran

Because groundwater quality representatives for drinking usage (i.e., Schuler method, Nitrate and Groundwater Quality Index) have been abruptly changing due to extreme events induced by global climate change and over-abstracting, applying an efficient tool for their assessments is vitally important. While hotspot analysis is introduced as an efficient tool concentrating on sharp changes in groundwater quality, it has not been closely examined. Accordingly, this study is an attempt to determine the groundwater quality proxies and assess them through hotspot and accumulated hotspot analyses. To this end, a GIS-based hotspot analysis (HA) applying Getis-Ord Gi* statistics was used. The accumulated hotspot analysis was launched to identify the Groundwater Quality Index (AHA-GQI). Moreover, Schuler method (AHA-SM) was utilized to determine the maximum levels (ML) for the hottest hotspot and the lowest levels (LL) for the coldest cold-spot, and compound levels (CL). The results revealed that a significant correlation (r = 0.8) between GQI and SM was observed. However, the correlation between GQI and nitrate was not significant and the correlation between SM and nitrate was so low (r = 0.298, sig > 0.05). The results also demonstrated that using hotspot analysis on only GQI, the correlation between GQI and SM increased from 0.8 to 0.856, while using hotspot analysis on both GQI and SM increased the correlation to 0.945. Likewise, when GQI was subjected to hotspot analysis and SM underwent accumulated hotspot analysis (i.e., AHA-SM (ML)), the correlation degree increased to the highest extent (i.e., 0.958), indicating the usefulness of including the hotspot analysis and accumulated hotspot analysis in the evaluation of groundwater quality.

Groundwater fluoride and nitrate contamination and associated human health risk assessment in South Punjab, Pakistan

Consumption of high fluoride (F^-) and nitrate (NO₃^-) containing water may pose serious health hazards. One hundred sixty-one groundwater samples were collected from drinking wells in Khushab district, Punjab Province, Pakistan, to determine the causes of elevated F^- and NO₃^- concentrations, and to estimate the human health risks posed by groundwater contamination. The results showed pH of the groundwater samples ranged from slightly neutral to alkaline, and Na⁺ and HCO₃^- ions dominated the groundwater. Piper diagram and bivariate plots indicated that the key factors regulating groundwater hydrochemistry were weathering of silicates, dissolution of evaporates, evaporation, cation exchange, and anthropogenic activities. The F^- content of groundwater ranged from 0.06 to 7.9 mg/L, and 25.46% of groundwater samples contained high-level fluoride concentration (F^-  > 1.5 mg/L), which exceeds the (WHO Guidelines for drinking-water quality: incorporating the first and second addenda, WHO, Geneva, 2022) guidelines of drinking-water quality. Inverse geochemical modeling indicates that weathering and dissolution of fluoride-rich minerals were the primary causes of F^- in groundwater. High F^- can be attributed to low concentration of calcium-containing minerals along the flow path. The concentrations of NO₃^- in groundwater varied from 0.1 to 70 mg/L; some samples are slightly exceeding the (WHO Guidelines for drinking-water quality: incorporating the first and second addenda, WHO, Geneva, 2022) guidelines for drinking-water quality. Elevated NO₃^- content was attributed to the anthropogenic activities revealed by PCA analysis. The high levels of nitrates found in the study region are a result of various human-caused factors, including leaks from septic systems, the use of nitrogen-rich fertilizers, and waste from households, farming operations, and livestock. The hazard quotient (HQ) and total hazard index (THI) of F^- and NO₃^- showed high non-carcinogenic risk (> 1) via groundwater consumption, demonstrating a high potential risk to the local population. This study is significant because it is the most comprehensive examination of water quality, groundwater hydrogeochemistry, and health risk assessment in the Khushab district to date, and it will serve as a baseline for future studies. Some sustainable measures are urgent to reduce the F^- and NO₃^- content in the groundwater.

Application of machine learning in groundwater quality modeling - A comprehensive review

Groundwater is a crucial resource across agricultural, civil, and industrial sectors. The prediction of groundwater pollution due to various chemical components is vital for planning, policymaking, and management of groundwater resources. In the last two decades, the application of machine learning (ML) techniques for groundwater quality (GWQ) modeling has grown exponentially. This review assesses all supervised, semi-supervised, unsupervised, and ensemble ML models implemented to predict any groundwater quality parameter, making this the most extensive modern review on this topic. Neural networks are the most used ML model in GWQ modeling. Their usage has declined in recent years, giving rise to more accurate or advanced techniques such as deep learning or unsupervised algorithms. Iran and the United States lead the world in areas modeled, with a wealth of historical data available. Nitrate has been modeled most exhaustively, targeted by nearly half of all studies. Advancements in future work will be made with further implementation of deep learning and explainable artificial intelligence or other cutting-edge techniques, application of these techniques for sparsely studied variables, the modeling of new or unique study areas, and the implementation of ML techniques for groundwater quality management.