Implementation of an automated beach water quality nowcast system at ten California oceanic beaches

Know Before You Go: Data-Driven Beach Water Quality Forecasting

Forecasting environmental hazards is critical in preventing or building resilience to their impacts on human communities and ecosystems. Environmental data science is an emerging field that can be harnessed for forecasting, yet more work is needed to develop methodologies that can leverage increasingly large and complex data sets for decision support. Here, we design a data-driven framework that can, for the first time, forecast bacterial standard exceedances at marine beaches with 3 days lead time. Using historical data sets collected at two California sites, we train nearly 400 forecast models using statistical and machine learning techniques and test forecasts against predictions from both a naive "persistence" model and a baseline nowcast model. Overall, forecast models are found to have similar sensitivities and specificities to the persistence model, but significantly higher areas under the ROC curve (a metric distinguishing a model's ability to effectively parse classes across decision thresholds), suggesting that forecasts can provide enhanced information beyond past observations alone. Forecast model performance at all lead times was similar to that of nowcast models. Together, results suggest that integrating the forecasting framework developed in this study into beach management programs can enable better public notification and aid in proactive pollution and health risk management.

High-frequency fecal indicator bacteria (FIB) observations to assess water quality drivers at an enclosed beach

Fecal indicator bacteria (FIB) are monitored at beaches to assess water quality and associated health risk from recreational exposure. However, monitoring is generally conducted infrequently (i.e. weekly or less often), potentially leading to inaccurate assessment of water quality at a beach at the time of use. While some work has shown that FIB in marine environments can vary over short (e.g. subhourly) time scales, that work has been mainly focused on 'open' beaches. 'Enclosed' beaches-those that are partially barriered from exchange with offshore water and thus have different residence times and mixing dynamics in the nearshore environment-have been less studied. Here we present results from a high-frequency (once per 30 minutes) FIB sampling event conducted within a Central California, USA, harbor over 48 hours. FIB concentrations at this enclosed site were more variable at high-frequencies than what has been reported at open beach sites. Correlation and regression analyses showed FIB concentrations were most strongly associated with chlorophyll a concentration, turbidity, wind speed, and tide level. Results indicate the importance of measuring FIB concentrations and explanatory environmental parameters at appropriate temporal resolutions when conducting water quality monitoring or source tracking studies. Overall, this work highlights how high-frequency sampling can effectively provide information about water quality dynamics at beaches of interest.

Waterborne virus transport and the associated risks in a large lake

Waterborne enteric viruses in lakes, especially at recreational water sites, may have a negative impact on human health. However, their fate and transport in lakes are poorly understood. In this study, we propose a coupled water quality and quantitative microbial risk assessment (QMRA) model to study the transport, fate and infection risk of four common waterborne viruses (adenovirus, enterovirus, norovirus and rotavirus), using Lake Geneva as a study site. The measured virus load in raw sewage entering the lake was used as the source term in the water quality simulations for a hypothetical scenario of discharging raw wastewater at the lake surface. After discharge into the lake, virus inactivation was modeled as a function of water temperature and solar irradiance that varied both spatially and temporally during transport throughout the lake. Finally, the probability of infection, while swimming at a popular beach, was quantified and compared among the four viruses. Norovirus was found to be the most abundant virus that causes an infection probability that is at least 10 times greater than the other viruses studied. Furthermore, environmental inactivation was found to be an essential determinant in the infection risks posed by viruses to recreational water users. We determined that infection risks by enterovirus and rotavirus could be up to 1000 times lower when virus inactivation by environmental stressors was accounted for compared with the scenarios considering hydrodynamic transport only. Finally, the model highlighted the role of the wind field in conveying the contamination plume and hence in determining infection probability. Our simulations revealed that for beaches located west of the sewage discharge, the infection probability under eastward wind was 43% lower than that under westward wind conditions. This study highlights the potential of combining water quality simulation and virus-specific risk assessment for a safe water resources usage and management.

Source, fate, transport and modelling of selected emerging contaminants in the aquatic environment: Current status and future perspectives

The occurrence of emerging contaminants (ECs), such as pharmaceuticals and personal care products (PPCPs), perfluoroalkyl and polyfluoroalkyl substances (PFASs) and endocrine-disrupting chemicals (EDCs) in aquatic environments represent a major threat to water resources due to their potential risks to the ecosystem and humans even at trace levels. Mathematical modelling can be a useful tool as a comprehensive approach to study their fate and transport in natural waters. However, modelling studies of the occurrence, fate and transport of ECs in aquatic environments have generally received far less attention than the more widespread field and laboratory studies. In this study, we reviewed the current status of modelling ECs based on selected representative ECs, including their sources, fate and various mechanisms as well as their interactions with the surrounding environments in aquatic ecosystems, and explore future development and perspectives in this area. Most importantly, the principles, mathematical derivations, ongoing development and applications of various ECs models in different geographical regions are critically reviewed and discussed. The recommendations for improving data quality, monitoring planning, model development and applications were also suggested. The outcomes of this review can lay down a future framework in developing a comprehensive ECs modelling approach to help researchers and policymakers effectively manage water resources impacted by rising levels of ECs.

Analysis and prediction of water quality using deep learning and auto deep learning techniques

Natural water sources like ponds, lakes and rivers are facing a great threat because of activities like discharge of untreated industrial effluents, sewage water, wastes, etc. It is mandatory to examine the water quality to ensure that only safe water is available for consumption. Traditional methods of water quality inspection are a cumbersome process and hence, Artificial Intelligence (AI) can be used as a catalyst for this process. AutoDL is an upcoming field to automate deep learning pipelines and enables model creation and interpretation with minimal code. However, it is still in the nascent stage. This work explores the suitability of adopting AutoDL for Water Quality Assessment by drawing a comparison between AutoDL and a conventional models and analysis to foresee the quality of the water, an appropriate class based on Water Quality Index segregating water bodies into different classes. The accuracy of conventional DL is 1.8% higher than that of AutoDL for binary class water data. The accuracy of conventional DL is 1% higher than that of AutoDL for multiclass water data. The accuracy of conventional model was ~98% to ~99% whereas AutoDL method yielded ~96% to ~98%. However, the AutoDL model ease the task of finding the appropriate DL model and proved better efficiency without manual intervention.

Advancing prediction of emerging contaminants in a tropical reservoir with general water quality indicators based on a hybrid process and data-driven approach

Monitoring and predicting the occurrence and dynamic distributions of emerging contaminants (ECs) in the aquatic environment has always been a great challenge. This study aims to explore the potential of fully utilizing the advantages of combining traditional process-based models (PBMs) and data-driven models (DDMs) with general water quality indicators in terms of improving the accuracy and efficiency of predicting ECs in aquatic ecosystems. Two representative ECs, namely Bisphenol A (BPA) and N, N-diethyltoluamide (DEET), in a tropical reservoir were chosen for this study. A total of 36 DDMs based on different input datasets using Artificial Neural Networks (ANN) and Random Forests (RF) were examined in three case studies. The models were applied in prognosis validation based on easily accessible data on water quality indicators. Our results revealed that all the models yielded good fits when compared to the observed data. These new insights into the advantages using the combination of traditional PBMs and DDMs with general water quality datasets help to overcome the constraints in terms of model accuracy and efficiency as well as technical and budget limitations due to monitoring surveys and laboratory experiments in the study of fate and transport of ECs in aquatic environments.

Machine learning methods for imbalanced data set for prediction of faecal contamination in beach waters

Predicting water contamination by statistical models is a useful tool to manage health risk in recreational beaches. Extreme contamination events, i.e. those exceeding normative are generally rare with respect to bathing conditions and thus the data is said to be imbalanced. Modeling and predicting those rare events present unique challenges. Here we introduce and evaluate several machine learning techniques and metrics to model imbalanced data and evaluate model performance. We do so by using a) simulated data-sets and b) a real data base with records of faecal coliform abundance monitored for 10 years in 21 recreational beaches in Uruguay (N ≈ 19000) using in situ and meteorological variables. We discuss advantages and disadvantages of the methods and provide a simple guide to perform models for a general audience. We also provide R codes to reproduce model fitting and testing. We found that most Machine Learning techniques are sensitive to imbalance and require specific data pre-treatment (e.g. upsampling) to improve performance. Accuracy (i.e. correctly classified cases over total cases) is not adequate to evaluate model performance on imbalanced data set. Instead, true positive rates (TPR) and false positive rates (FPR) are recommended. Among the 52 possible candidate algorithms tested, the stratified Random forest presented the better performance improving TPR in 50% with respect to baseline (0.4) and outperformed baseline in the evaluated metrics. Support vector machines combined with upsampling method or synthetic minority oversampling technique (SMOTE) performed well, similar to Adaboost with SMOTE. These results suggests that combining modeling strategies is necessary to improve our capacity to anticipate water contamination and avoid health risk.

Cyanotoxin mixture models: Relating environmental variables and toxin co-occurrence to human exposure risk

Toxic cyanobacterial blooms, often containing multiple toxins, are a serious public health issue. However, there are no known models that predict a cyanotoxin mixture (anatoxin-a, microcystin, saxitoxin). This paper presents two cyanotoxin mixture models (MIX) and compares them to two microcystin (MC) models from data collected in 2016-2017 from three recurring cyanobacterial bloom locations in Kabetogama Lake, Voyageurs National Park (Minnesota, USA). Models include those using near-real-time environmental variables (readily available) and those using additional comprehensive variables (based on laboratory analyses). Comprehensive models (R² = 0.87 MC; R² = 0.86 MIX) explained more variability than the environmental models (R² = 0.58 MC; R² = 0.57 MIX). Although neither MIX model was a better fit than the MC models, the MIX models produced no false negatives in the calibration dataset, indicating that all observations above regulatory guidelines were simulated by the MIX models. This is the first known use of Virtual Beach software for a cyanotoxin mixture model, and the methods used in this paper may be applicable to other lakes or beaches.

Designing a marine outfall to reduce microbial risk on a recreational beach: Field experiment and modeling

A marine outfall can be a wastewater management system that discharges sewage and stormwater into the sea; hence, it is a source of microbial pollution on recreational beaches, including antibiotic resistant genes (ARGs), which lead to an increase in untreatable diseases. In this regard, a marine outfall must be efficiently located to mitigate these risks. This study aimed to 1) investigate the spatiotemporal variability of Escherichia coli (E. coli) and ARGs on a recreational beach and 2) design marine outfalls to reduce microbial risks. For this purpose, E. coli and ARGs with influential environmental variables were intensively monitored on Gwangalli beach, South Korea in this study. Environmental fluid dynamic code (EFDC) was used and calibrated using the monitoring data, and 12 outfall extension scenarios were explored (6 locations at 2 depths). The results revealed that repositioning the marine outfall can significantly reduce the concentrations of E. coli and ARGs on the beach by 46-99%. Offshore extended outfalls at the bottom of the sea reduced concentrations of E. coli and ARGs on the beach more effectively than onshore outfalls at the sea surface. These findings could be helpful in establishing microbial pollution management plans at recreational beaches in the future.

A Day at the Beach: Enabling Coastal Water Quality Prediction with High-Frequency Sampling and Data-Driven Models

To reduce the incidence of recreational waterborne illness, fecal indicator bacteria (FIB) are measured to assess water quality and inform beach management. Recently, predictive FIB models have been used to aid managers in making beach posting and closure decisions. However, those predictive models must be trained using rich historical data sets consisting of FIB and environmental data that span years, and many beaches lack such data sets. Here, we investigate whether water quality data collected during discrete short duration, high-frequency beach sampling events (e.g., samples collected at sub-hourly intervals for 24-48 h) are sufficient to train predictive models that can be used for beach management. We use data collected during six high-frequency sampling events at three California marine beaches and train a total of 126 models using common data-driven techniques. Tide, solar irradiation, water temperature, significant wave height, and offshore wind speed were found to be the most important environmental variables in the models. We validate the predictive performance of models using withheld data. Random forests are consistently the top performing model type. Overall, we find that data-driven models trained using high-frequency FIB and environmental data perform well at predicting water quality and can be used to inform public health decisions at beaches.

Microbial Indicators of Fecal Pollution: Recent Progress and Challenges in Assessing Water Quality

PURPOSE OF REVIEW

Fecal contamination of water is a major public health concern. This review summarizes recent developments and advancements in water quality indicators of fecal contamination.

RECENT FINDINGS

This review highlights a number of trends. First, fecal indicators continue to be a valuable tool to assess water quality and have expanded to include indicators able to detect sources of fecal contamination in water. Second, molecular methods, particularly PCR-based methods, have advanced considerably in their selected targets and rigor, but have added complexity that may prohibit adoption for routine monitoring activities at this time. Third, risk modeling is beginning to better connect indicators and human health risks, with the accuracy of assessments currently tied to the timing and conditions where risk is measured. Research has advanced although challenges remain for the effective use of both traditional and alternative fecal indicators for risk characterization, source attribution and apportionment, and impact evaluation.

Atmospheric rivers impact California's coastal water quality via extreme precipitation

Precipitation in California is projected to become more volatile: less frequent but more extreme as global warming pushes midlatitude frontal cyclones further poleward while bolstering the atmospheric rivers (ARs), which tend to produce the region's extreme rainfall. Pollutant accumulation and delivery to coastal waters can be expected to increase, as lengthening dry spells will be increasingly punctuated by more extreme precipitation events. Coastal pollution exposes human populations to high levels of fecal bacteria and associated pathogens, which can cause a variety of health impacts. Consequently, studying the impact of atmospheric rivers as the mechanism generating pulses of water pollution in coastal areas is relevant for public health and in the context of climate change. We aimed to quantify the links between precipitation events and water quality in order to explore meteorological causes as first steps toward effective early warning systems for the benefit of population health in California and beyond. We used historical gridded daily precipitation and weekly multiple fecal bacteria indicators at ~500 monitoring locations in California's coastal waters to identify weekly associations between precipitation and water quality during 2003-09 using canonical correlation analysis to account for the nested/clustered nature of longitudinal data. We then quantified, using a recently published catalog of atmospheric rivers, the proportion of coastal pollution events attributable to ARs. Association between precipitation and fecal bacteria was strongest in Southern California. Over two-thirds of coastal water pollution spikes exceeding one standard deviation were associated with ARs. This work highlights the importance of skillful AR landfall predictions in reducing vulnerability to extreme weather improving resilience of human populations in a varying and changing climate. Quantifying the impacts of ARs on waterborne diseases is important for planning effective preventive strategies for public health.

The disparity between regulatory measurements of E. coli in public bathing waters and the public expectation of bathing water quality

The main objectives of the European Union (EU) Bathing Water Directive (BWD) 2006/7/EC are to safeguard public health and protect designated aquatic environments from microbial pollution. The BWD is implemented through legislation by individual EU Member States and uses faecal indicator organisms (FIOs) as microbial pollution compliance parameters to determine season-end bathing water classifications (either 'Excellent', 'Good', 'Sufficient' or 'Poor'). These classifications are based on epidemiological studies that have linked human exposure to FIOs with the risk of contracting a gastrointestinal illness (GI). However, understanding public attitudes towards bathing water quality, together with perceptions of relative exposure risks, is often overlooked and yet critically important for informing environmental management decisions at the beach and ensuring effective risk communication. Therefore, this study aimed to determine the effectiveness of current regulatory strategies for informing beach users about bathing water quality, and to assess public understanding of the BWD classifications in terms of exposure risk and public health. Two UK designated bathing waters were selected as case studies, and questionnaires were deployed to beach-users. The bathing waters had different classification histories and both had electronic signage in operation for communicating daily water quality predictions. The majority of respondents did not recognise the standardised EU bathing water quality classification signs, and were unaware of information boards or the electronic signs predicting the water quality on that particular day. In general, respondents perceived the bathing water at their respective beach to be either 'good' or 'sufficient', which were also the lowest classifications of water quality they would be willing to accept for bathing. However, the lowest level of risk of contracting a gastrointestinal illness that respondents would be willing to accept suggested a significant misunderstanding of the BWD classification system, with the majority (91%) of respondents finding only a <1% risk level acceptable. The 'Good' classification is much less stringent in terms of likelihood of GI. This study has shown that the current public understanding of the BWD classifications in terms of exposure risk and public health is limited, and an investment in methods for disseminating information to the public is needed in order to allow beach-users to make more informed decisions about using bathing waters.