Spatiotemporal trends of recovery from lead contamination in Flint, MI as revealed by crowdsourced water sampling

High resolution data visualization and machine learning prediction of free chlorine residual in a green building water system

People spend most of their time indoors and are exposed to numerous contaminants in the built environment. Water management plans implemented in buildings are designed to manage the risks of preventable diseases caused by drinking water contaminants such as opportunistic pathogens (e.g., Legionella spp.), metals, and disinfection by-products (DBPs). However, specialized training required to implement water management plans and heterogeneity in building characteristics limit their widespread adoption. Implementation of machine learning and artificial intelligence (ML/AI) models in building water settings presents an opportunity for faster, more widespread use of data-driven water quality management approaches. We demonstrate the utility of Random Forest and Long Short-Term Memory (LSTM) ML models for predicting a key public health parameter, free chlorine residual, as a function of data collected from building water quality sensors (ORP, pH, conductivity, and temperature) as well as WiFi signals as a proxy for building occupancy and water usage in a "green" Leadership in Energy and Environmental Design (LEED) commercial and institutional building. The models successfully predicted free chlorine residual declines below 0.2 ppm, a common minimum reference level for public health protection in drinking water distribution systems. The predictions were valid up to 5 min in advance, and in some cases reasonably accurate up to 24 h in advance, presenting opportunities for proactive water quality management as part of a sense-analyze-decide framework. An online data dashboard for visualizing water quality in the building is presented, with the potential to link these approaches for real-time water quality management.

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.

Study on the risk of soil heavy metal pollution in typical developed cities in eastern China

Enrichment of heavy metals in urban soils has become a major regional environmental risk. At present, research on the soil heavy metals in cities lacks risk spatial correlation analyses between different heavy metals, and there is a relative lack of assessments of the ecological and health risks. We selected Wuxi, a typical developed city of eastern China, collected and tested the contents of heavy metals in the urban soils of Wuxi in May 2020. Combined with Pb isotope analysis, ecological and health risk assessment, we found that the high heavy metal concentrations in Wuxi are mainly located in the central and western regions, and that the changes in spatial fluctuation are relatively small. The Pb isotopes in the urban soils of Wuxi are distributed in areas, such as those are related to coal combustion, automobile exhaust and urban garbage, indicating that the heavy metals in the urban soils of Wuxi are affected by human activities such as coal combustion and automobile exhaust. The average value of the potential ecological risk index of soil heavy metal Cd is 80.3 (the threshold: 40), which represents a high-risk state. Whether adults or children, the risk of soil heavy metals via ingestion is much higher than that through skin exposure. High health risk values are present in the central area of Wuxi and decrease in a ring-shaped pattern, which is similar to the population distribution of Wuxi and greatly increases the potential risk from soil heavy metals, which should be given close attention. We should develop and use clean energy to replace petroleum fossil fuels, especially in densely populated areas. This study provides technical support for the prevention and control of urban heavy metal pollution.

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

The presence of lead in drinking water creates a public health crisis, as lead causes neurological damage at low levels of exposure. The objective of this research is to explore modeling approaches to predict the risk of lead at private drinking water systems. This research uses Bayesian Network approaches to explore interactions among household characteristics, geological parameters, observations of tap water, and laboratory tests of water quality parameters. A knowledge discovery framework is developed by integrating methods for data discretization, feature selection, and Bayes classifiers. Forward selection and backward selection are explored for feature selection. Discretization approaches, including domain-knowledge, statistical, and information-based approaches, are tested to discretize continuous features. Bayes classifiers that are tested include General Bayesian Network, Naive Bayes, and Tree-Augmented Naive Bayes, which are applied to identify Directed Acyclic Graphs (DAGs). Bayesian inference is used to fit conditional probability tables for each DAG. The Bayesian framework is applied to fit models for a dataset collected by the Virginia Household Water Quality Program (VAHWQP), which collected water samples and conducted household surveys at 2,146 households that use private water systems, including wells and springs, in Virginia during 2012 and 2013. Relationships among laboratory-tested water quality parameters, observations of tap water, and household characteristics, including plumbing type, source water, household location, and on-site water treatment are explored to develop features for predicting water lead levels. Results demonstrate that Naive Bayes classifiers perform best based on recall and precision, when compared with other classifiers. Copper is the most significant predictor of lead, and other important predictors include county, pH, and on-site water treatment. Feature selection methods have a marginal effect on performance, and discretization methods can greatly affect model performance when paired with classifiers. Owners of private wells remain disadvantaged and 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 for private wells. Insight gained from models can be used to identify water quality parameters, plumbing characteristics, and household variables that increase the likelihood of high water lead levels to inform decisions about lead testing and treatment.

Tracking reduction of water lead levels in two homes during the Flint Federal Emergency

A Federal Emergency was declared in Flint, MI, on January 16, 2016, 18-months after a switch to Flint River source water without phosphate corrosion control. Remedial actions to resolve the corresponding lead in water crisis included reconnection to the original Lake Huron source water with orthophosphate, implementing enhanced corrosion control by dosing extra orthophosphate, a "Flush for Flint" program to help clean out loose leaded sediment from service lines and premise plumbing, and eventually lead service line replacement. Independent sampling over a period of 37 months (January 2016-February 2019) was conducted by the United States Environmental Protection Agency and Virginia Tech to evaluate possible human exposure via normal flow (∼2-3 L/min) sampling at the cold kitchen tap, and to examine the status of loose deposits from the service line and the premise plumbing via high-velocity flushing (∼12-13 L/min) from the hose bib. The sampling results indicated that high lead in water persisted for more than a year in two Flint homes due to a large reservoir of lead deposits. The effects of a large reservoir of loose lead deposits persisted until the lead service line was completely removed in these two anomalous homes. As water conservation efforts are implemented in many areas of the country, problems with mobile lead reservoirs in service lines are likely to pose a human health risk.