Developing a framework for classifying water lead levels at private drinking water systems: A Bayesian Belief Network approach

Advances and future directions of environmental risk research: A bibliometric review

Environmental risk is one of the world's most significant threats, projected to be the leading risk over the next decade. It has garnered global attention due to increasingly severe environmental issues, such as climate change and ecosystem degradation. Research and technology on environmental risks are gradually developing, and the scope of environmental risk study is also expanding. Here, we developed a tailored bibliometric method, incorporating co-occurrence network analysis, cluster analysis, trend factor analysis, patent primary path analysis, and patent map methods, to explore the status, hotspots, and trends of environment risk research over the past three decades. According to the bibliometric results, the publications and patents related to environmental risk have reached explosive growth since 2018. The primary topics in environmental risk research mainly involve (a) ecotoxicology risk of emerging contaminants (ECs), (b) environmental risk induced by climate change, (c) air pollution and health risk assessment, (d) soil contamination and risk prevention, and (e) environmental risk of heavy metal. Recently, the hotspots of this field have shifted into artificial intelligence (AI) based techniques and environmental risk of climate change and ECs. More research is needed to assess ecological and health risk of ECs, to formulize mitigation and adaptation strategies for climate change risks, and to develop AI-based environmental risk assessment and control technology. This study provides the first comprehensive overview of recent advances in environmental risk research, suggesting future research directions based on current understanding and limitations.

Modeling prevention behaviors during the COVID-19 pandemic using Bayesian belief networks and protection motivation theory

Prevention behaviors are important in mitigating the transmission of COVID-19. The protection motivation theory (PMT) links perceptions of risk and coping ability with the act of adopting prevention behaviors. The goal of this research is to test the application of the PMT in predicting adoption of prevention behaviors during the COVID-19 pandemic. Two research objectives are achieved to explore motivating factors for adopting prevention behaviors. (1) The first objective is to identify variables that are strong predictors of prevention behavior adoption. A data-driven approach is used to train Bayesian belief network (BBN) models using results of a survey ofN = 7797 $N=7797$ participants reporting risk perceptions and prevention behaviors during the COVID-19 pandemic. A large set of models are generated and analyzed to identify significant variables. (2) The second objective is to develop models based on the PMT to predict prevention behaviors. BBN models that predict prevention behaviors were developed using two approaches. In the first approach, a data-driven methodology trains models using survey data alone. In the second approach, expert knowledge is used to develop the structure of the BBN using PMT constructs. Results demonstrate that trust and experience with COVID-19 were important predictors for prevention measure adoption. Models that were developed using the PMT confirm relationships between coping appraisal, threat appraisal, and protective behaviors. Data-driven and PMT-based models perform similarly well, confirming the use of PMT in this context. Predicting adoption of social distancing behaviors provides insight for developing policies during pandemics.

Forecasting fish mortality from water and air quality data using deep learning models

The high rate of aquatic mortality incidents recorded in Taiwan and worldwide is creating an urgent demand for more accurate fish mortality prediction. Present study innovatively integrated air and water quality data to measure water quality degradation, and utilized deep learning methods to predict accidental fish mortality from the data. Keras library was used to build multilayer perceptron and long short-term memory models for training purposes, and the models' accuracies in fish mortality prediction were compared with that of the naïve Bayesian classifier. Environmental data from the 5 days before a fish mortality event proved to be the most important data for effective model training. Multilayer perceptron model reached an accuracy of 93.4%, with a loss function of 0.01, when meteorological and water quality data were jointly considered. It was found that meteorological conditions were not the sole contributors to fish mortality. Predicted fish mortality rate of 4.7% closely corresponded to the true number of fish mortality events during the study period, that is, four. A significant surge in fish mortality, from 20% to 50%, was noted when the river pollution index increased from 5.36 to 6.5. Moreover, the probability of fish mortality increased when the concentration of dissolved oxygen dropped below 2 mg/L. To mitigate fish mortality, ammonia nitrogen concentrations should be capped at 5 mg/L. Dissolved oxygen concentration was found to be the paramount factor influencing fish mortality, followed by the river pollution index and meteorological data. Results of the present study are expected to aid progress toward achieving the Sustainable Development Goals and to increase the profitability of water resources.

Predicting Groundwater PFOA Exposure Risks with Bayesian Networks: Empirical Impact of Data Preprocessing on Model Performance

The plethora of data on PFASs in environmental samples collected in response to growing concern about these chemicals could enable the training of machine-learning models for predicting exposure risks. However, differences in sampling and analysis methods across data sets must be reconciled through data preprocessing, and little information is available about how such manipulations affect the resulting models. This study evaluates how data preprocessing influences machine-learned Bayesian network models of PFOA in groundwater. We link 19 years of PFOA measurements from Minnesota, USA, to publicly available information about potential PFOA sources and factors that may influence their environmental fate. Nine different preprocessing methods were tested, and the resulting data sets were used to train models to predict the probability of PFOA ≥ 35 ppt, the 2017 Minnesota health advisory level. Different preprocessing approaches produced varying model structures with significantly different accuracies. Nonetheless, models showed similar relationships between predictor variables and PFOA exposure risks, and all models were relatively accurate, distinguishing wells at high risk from those at low risk for 82.0% to 89.0% of test data samples. There was a trade-off between data quality and model performance since a stricter data screening strategy decreased the sample size for model training.

The Behavior of Polymeric Pipes in Drinking Water Distribution System-Comparison with Other Pipe Materials

The inner walls of the drinking water distribution system (DWDS) are expected to be clean to ensure a safe quality of drinking water. Complex physical, chemical, and biological processes take place when water comes into contact with the pipe surface. This paper describes the impact of leaching different compounds from the water supply pipes into drinking water and subsequent risks. Among these compounds, there are heavy metals. It is necessary to prevent these metals from getting into the DWDS. Those compounds are susceptible to impacting the quality of the water delivered to the population either by leaching dangerous chemicals into water or by enhancing the development of microorganism growth on the pipe surface. The corrosion process of different pipe materials, scale formation mechanisms, and the impact of bacteria formed in corrosion layers are discussed. Water treatment processes and the pipe materials also affect the water composition. Pipe materials act differently in the flowing and stagnation conditions. Moreover, they age differently (e.g., metal-based pipes are subjected to corrosion while polymer-based pipes have a decreased mechanical resistance) and are susceptible to enhanced bacterial film formation. Water distribution pipes are a dynamic environment, therefore, the models that are used must consider the changes that occur over time. Mathematical modeling of the leaching process is complex and includes the description of corrosion development over time, correlated with a model for the biofilm formation and the disinfectants-corrosion products and disinfectants-biofilm interactions. The models used for these processes range from simple longitudinal dispersion models to Monte Carlo simulations and 3D modeling. This review helps to clarify what are the possible sources of compounds responsible for drinking water quality degradation. Additionally, it gives guidance on the measures that are needed to maintain stable and safe drinking water quality.

The Utility of Machine Learning Models for Predicting Chemical Contaminants in Drinking Water: Promise, Challenges, and Opportunities

PURPOSE OF REVIEW

This review aims to better understand the utility of machine learning algorithms for predicting spatial patterns of contaminants in the United States (U.S.) drinking water.

RECENT FINDINGS

We found 27 U.S. drinking water studies in the past ten years that used machine learning algorithms to predict water quality. Most studies (42%) developed random forest classification models for groundwater. Continuous models show low predictive power, suggesting that larger datasets and additional predictors are needed. Categorical/classification models for arsenic and nitrate that predict exceedances of pollution thresholds are most common in the literature because of good national scale data coverage and priority as environmental health concerns. Most groundwater data used to develop models were obtained from the United States Geological Survey (USGS) National Water Information System (NWIS). Predictors were similar across contaminants but challenges are posed by the lack of a standard methodology for imputation, pre-processing, and differing availability of data across regions. We reviewed 27 articles that focused on seven drinking water contaminants. Good performance metrics were reported for binary models that classified chemical concentrations above a threshold value by finding significant predictors. Classification models are especially useful for assisting in the design of sampling efforts by identifying high-risk areas. Only a few studies have developed continuous models and obtaining good predictive performance for such models is still challenging. Improving continuous models is important for potential future use in epidemiological studies to supplement data gaps in exposure assessments for drinking water contaminants. While significant progress has been made over the past decade, methodological advances are still needed for selecting appropriate model performance metrics and accounting for spatial autocorrelations in data. Finally, improved infrastructure for code and data sharing would spearhead more rapid advances in machine-learning models for drinking water quality.

Elevated water lead levels in schools using water from on-site wells

Only 8% of US public schools operate their own community water systems, and thus are subject to the federal Lead and Copper Rule's regulation of water lead levels (WLLs). To date, the absence of parallel water testing data for all other schools has prevented the comparison of WLLs with schools that do not face federal regulation. This study compiled and analyzed newly available school-level WLL data that included water source (on-site well water or public utility) and pipe material data for public schools in New York State located outside of New York City. Despite direct federal regulation, schools that used water from on-site wells had a substantially higher percentage of water fixtures with elevated WLLs. Schools that used both on-site well water and iron pipes in their water distribution system had the highest percentage of elevated fixtures. Variation in water treatment practices was identified as a potential contributing mechanism, as schools that used on-site well water were less likely to implement corrosion control. The study concluded that information about water source and premise plumbing material may be useful to policymakers targeting schools for testing and remediation.

Developing early warning systems to predict water lead levels in tap water for private systems

Lead is a chemical contaminant that threatens public health, and high levels of lead have been identified in drinking water at locations across the globe. Under-served populations that use private systems for drinking water supplies may be at an elevated level of risk because utilities and governing agencies are not responsible for ensuring that lead levels meet the Lead and Copper Rule at these systems. Predictive models that can be used by residents to assess water quality threats in their households can create awareness of water lead levels (WLLs). This research explores and compares the use of statistical models (i.e., Bayesian Belief classifiers) and machine learning models (i.e., ensemble of decision trees) for predicting WLLs. Models are developed using a dataset collected by the Virginia Household Water Quality Program (VAHWQP) at approximately 8000 households in Virginia during 2012-2017. The dataset reports laboratory-tested water quality parameters at households, location information, and household and plumbing characteristics, including observations of water odor, taste, discoloration. Some water quality parameters, such as pH, iron, and copper, can be measured at low resolution by residents using at-home water test kits and can be used to predict risk of WLLs. The use of at-home water quality test kits was simulated through the discretization of water quality parameter measurements to match the resolution of at-home water quality test kits and the introduction of error in water quality readings. Using this approach, this research demonstrates that low-resolution data collected by residents can be used as input for models to estimate WLLs. Model predictability was explored for a set of at-home water quality test kits that observe a variety of water quality parameters and report parameters at a range of resolutions. The effects of the timing of water sampling (e.g., first-draw vs. flushed samples) and error in kits on model error were tested through simulations. The prediction models developed through this research provide a set of tools for private well users to assess the risk of lead contamination. Models can be implemented as early warning systems in citizen science and online platforms to improve awareness of drinking water threats.

Correlation between As, Cd, Hg, Pb and Sn concentration in human milk and breastfeeding mothers' food consumption: a systematic review and infants' health risk assessment

Mothers' food and water consumption appear to be determining factors for infants' potentially toxic elements exposure through human milk. Therefore, this systematic review aimed to assess correlations between As, Cd, Hg, Pb and/or Sn concentration in human milk and breastfeeding mothers' food consumption, with later infants' health risk assessment. Estimated Daily Intakes of such elements by infants were also calculated and compared with reference values (RfD or BMDL01). Among 5.663 identified studies, 23 papers remained for analysis. Potentially toxic elements concentration in human milk presented positive correlation with seafood (As, Hg), fresh vegetables (Hg, Cd), cereals (Hg, Cd), cheese, rice, potatoes, private and well-water supply (Pb), wild meat (Pb, Cd) and milk, dairy products, dried fruits and oilseeds (Cd) mothers' consumption. Red meat, caffeinated drinks, and dairy products consume presented negative correlations (Pb). No correlations were found for Sn. Infants from three studies presented high Hg exposition through human milk (> 0. 1 μg/kg PC-1 day-1), as well as observed for Pb in one study (> 0. 5 μg/kg PC-1 day-1). Potentially toxic elements can damage infants' health when they are present in mothers' diet due to the infants' high vulnerability. Therefore, these results raise important issues for public health.Supplemental data for this article is available online at https://doi.org/10.1080/10408398.2022.2056869 .

A new approach to a legacy concern: Evaluating machine-learned Bayesian networks to predict childhood lead exposure risk from community water systems

Lead in drinking water continues to put children at risk of irreversible neurological impairment. Understanding drinking water system characteristics that influence blood lead levels is needed to prevent ongoing exposures. This study sought to assess the relationship between children's blood lead levels and drinking water system characteristics using machine-learned Bayesian networks. Blood lead records from 2003 to 2017 for 40,742 children in Wake County, North Carolina were matched with the characteristics of 178 community water systems and sociodemographic characteristics of each child's neighborhood. Bayesian networks were machine-learned to evaluate the drinking water variables associated with blood lead levels ≥2 μg/dL and ≥5 μg/dL. The model was used to predict geographic areas and water utilities with increased lead exposure risk. Drinking water characteristics were not significantly associated with children's blood lead levels ≥5 μg/dL but were important predictors of blood lead levels ≥2 μg/dL. Whether 10% of water samples exceeded 2 ppb of lead in the most recent year prior to the blood test was the most important water system predictor and increased the risk of blood lead levels ≥2 μg/dL by 42%. The model achieved an area under the receiver operating characteristic curve of 0.792 (±0.8%) during ten-fold cross validation, indicating good predictive performance. Water system characteristics may thus be used to predict areas that are at risk of higher blood lead levels. Current drinking water regulatory thresholds for lead may be insufficient to detect the levels in drinking water associated with children's blood lead levels.

Identifying schools at high-risk for elevated lead in drinking water using only publicly available data

Estimating the risk of lead contamination of schools' drinking water at the State level is a complex, important, and unexplored challenge. Variable water quality among water systems and changes in water chemistry during distribution affect lead dissolution rates from pipes and fittings. In addition, the locations of lead-bearing plumbing materials are uncertain. We tested the capability of six machine learning models to predict the likelihood of lead contamination of drinking water at the schools' taps using only publicly available datasets. The predictive features used in the models correspond to those with a proven correlation to the dominant, but commonly unavailable, factors that govern lead leaching: the presence of lead-bearing plumbing materials and water quality conducive to lead corrosion. By combining water chemistry data from public reports, socioeconomic information from the US census, and spatial features using Geographic Information Systems, we trained and tested models to estimate the likelihood of lead contaminated tap water in over 8,000 schools across California and Massachusetts. Our best-performing model was a Random Forest, with a 10-fold cross validation score of 0.88 for Massachusetts and 0.78 for California using the average Area Under the Receiver Operating Characteristic Curve (ROC AUC) metric. The model was then used to assign a lead leaching risk category to half of the schools across California (the other half was used for training). There was good agreement between the modeled risk categories and the actual lead leaching outcomes for every school; however, the model overestimated the lead leaching risk in up to 17% of the schools. This model is the first of its kind to offer a tool to predict the risk of lead leaching in schools at the State level. Further use of this model can help deploy limited resources more effectively to prevent childhood lead exposure from school drinking water.