IoT-based Edge Computing (IoTEC) for Improved Environmental Monitoring.

This research considered several applications of a coupled Internet of Things sensor network with Edge Computing (IoTEC) for improved environmental monitoring. Two pilot applications, covering environmental monitoring of vapor intrusion and system performance of wastewater-based algae cultivation, were designed to compare data latency, energy consumption, and economic cost between the IoTEC approach and the conventional sensor monitoring method. The results show that the IoTEC monitoring approach, compared with conventional IoT sensor networks, could significantly reduce data latency by 13%, and the amount of data transmission decreased by an average of 50%. In addition, the IoTEC method can increase the duration of power supply by 130%. Collectively, these improvements could lead to a compelling cost reduction of 55% - 82% per year for monitoring vapor intrusion at five houses, with more houses leading to more significant savings. Additionally, our results demonstrate the feasibility of deploying machine learning tools at edge servers for more advanced data processing and analysis.

Development and performance of a machine learning-based tool that predicts influent flow to a WRF 72 h in advance and integrates with existing wet weather nutrient management protocols.

Influent flow to the 75 mgd Neuse River Resource Recovery Facility (NRRRF) was modeled using machine learning. The trained model can predict hourly flow 72 h in advance. This model was deployed in July 2020, and has been in operation over two and a half years. The model's mean absolute error in training was 2.6 mgd, and mean absolute error has ranged from 10 to 13 mgd in deployment for any point during the wet weather event when predicting 12 h in advance. As a result of this tool, plant staff have optimized the use of their 32 MG wet weather equalization basin, using it approximately 10 times and never exceeding its volume. PRACTITIONER POINTS: A machine learning model was developed to predict influent flow to a WRF 72 h in advance. Selecting the appropriate model, variables, and properly characterizing the system are important considerations in machine learning modeling. This model was developed using free open source software/code (Python) and deployed securely using an automated Cloud-based data pipeline. This tool has been in operation for over 30 months and continues to make accurate predictions. Machine learning combined with subject matter expertise can greatly benefit the water industry.

Unsupervised learning methods for efficient geographic clustering and identification of disease disparities with applications to county-level colorectal cancer incidence in California.

Many public health policymaking questions involve data subsets representing application-specific attributes and geographic location. We develop and evaluate standard and tailored techniques for clustering via unsupervised learning (UL) algorithms on such amalgamated (dual-domain) data sets. The aim of the associated algorithms is to identify geographically efficient clusters that also maximize the number of statistically significant differences in disease incidence and demographic variables across top clusters. Two standard UL approaches, k means with k++ initialization (k++) and the standard self-organizing map (SSOM), are considered along with a new, tailored version of the SOM (TSOM). The TSOM algorithm involves optimization of a customized objective function with terms promoting individual geographic cluster cohesion while also maximizing the number of differences across clusters, and two hyper-parameters controlling the relative weighting of geographic and attribute subspaces in a non-Euclidean distance measure within the clustering problem. The performance of these three techniques (k++, SSOM, TSOM) is compared and evaluated in the context of a data set for colorectal cancer incidence in the state of California, at the level of individual counties. Clusters are visualized via chloropleth maps and ordered graphs are also used to illustrate disparities in disease incidence among four identity groups. While all three approaches performed well, the TSOM identified the largest number of disease and demographic disparities while also yielding more geographically efficient top clusters. Techniques presented in this study are relevant to applications including the delivery of health care resources and identifying disparities among identity groups, and to questions involving coordination between county- and state-level policymakers.

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.

Predicting the risk of GenX contamination in private well water using a machine-learned Bayesian network model.

Per- and polyfluoroalkyl substances (PFAS) are emerging contaminants that pose significant challenges in mechanistic fate and transport modeling due to their diverse and complex chemical characteristics. Machine learning provides a novel approach for predicting the spatial distribution of PFAS in the environment. We used spatial location information to link PFAS measurements from 1207 private drinking water wells around a fluorochemical manufacturing facility to a mechanistic model of PFAS air deposition and to publicly available data on soil, land use, topography, weather, and proximity to multiple PFAS sources. We used the resulting linked data set to train a Bayesian network model to predict the risk that GenX, a member of the PFAS class, would exceed a state provisional health goal (140 ng/L) in private well water. The model had high accuracy (ROC curve index for five-fold cross-validation of 0.85, 90% CI 0.84-0.87). Among factors significantly associated with GenX risk in private wells, the most important was the historic rate of atmospheric deposition of GenX from the fluorochemical manufacturing facility. The model output was used to generate spatial risk predictions for the study area to aid in risk assessment, environmental investigations, and targeted public health interventions.

Lead Distribution in Urban Soil in a Medium-Sized City: Household-Scale Analysis.

This study characterizes potential soil lead (Pb) exposure risk at the household scale in Greensboro, North Carolina, using an innovative combination of field sampling, statistical analysis, and machine-learning techniques. Soil samples were collected at the dripline, yard, and street side at 462 households (total sample size = 2310). Samples were analyzed for Pb and then combined with publicly available data on potential historic Pb sources, soil properties, and household and neighborhood demographic characteristics. This curated data set was then analyzed with statistical and machine-learning techniques to identify the drivers of potential soil Pb exposure risks and to build predictive models. Among all samples, 43% exceeded current guidelines for Pb in residential gardens. There were significant racial disparities in potential soil Pb exposure risk; soil Pb at the dripline increased by 19% for every 25% increase in the neighborhood population identifying as Black. A machine-learned Bayesian network model was able to classify residential parcels by risk of exceeding residential gardening standards with excellent reproducibility in cross validation. These findings underscore the need for targeted outreach programs to prevent Pb exposure in residential areas and demonstrate an approach for prioritizing outreach locations.

Mixotrophic Microalgae Biofilm: A Novel Algae Cultivation Strategy for Improved Productivity and Cost-efficiency of Biofuel Feedstock Production.

In this work, we studied a novel algae cultivation strategy, mixotrophic microalgae biofilm, to improve the productivity and cost-efficiency of algal biofuel production. In contrast to previous methods, this improved approach can achieve high productivity at low cost by harnessing the benefits of mixotrophic growth's high efficiency, i.e., capable of subsisting on inorganic and organic carbons thus unaffected by limited light, and microalgae biofilm's low harvesting cost. Our results, as one of the first studies of this type, proved that microalgae biofilms under mixotrophic condition exhibited significantly higher productivity and quality of biofuel feedstock: 2-3 times higher of biomass yield, 2-10 times higher of lipid accumulation, and 40-60% lower of ash content when compared to microalgae biofilms under autotrophic condition. In addition, we investigated the impact of cell-surface properties (hydrophobicity and roughness) on the growth activities of microalgae biofilms and found that the productivity of mixotrophic biofilms was significantly correlated with the surface hydrophobicity. Finally, our work demonstrated the applicability of integrating this novel cultivation method with wastewater for maximum efficiency. This study opens a new possibility to solve the long-lasting challenges of algal biofuel feedstock production, i.e., low productivity and high cost of algal cultivation.