Fall Creek Monitoring Station: Using Environmental Covariates To Predict Micropollutant Dynamics and Peak Events in Surface Water Systems

Prediction of nitrous oxide emission of a municipal wastewater treatment plant using LSTM-based deep learning models

Accurate assessment of greenhouse gas emissions from wastewater treatment plants is crucial for mitigating climate change. N2O is a potent greenhouse gas that is emitted from wastewater treatment plants during the biological denitrification process. In this study, we developed and evaluated deep learning models for predicting N2O emissions from a WWTP in Switzerland. Six key parameters were selected to obtain the optimal LSTM model by adjusting experimental parameter conditions. The optimal parameter condition was achieved with 150 neurons, the tanh activation function, the RMSprop optimization algorithm, a learning rate of 0.001, no dropout regularization, and a batch size of 128. Under the same conditions, we compared the performance of recurrent neural networks (RNNs) and Long Short-Term Memory (LSTM) networks. We found that LSTM models outperformed RNN models in predicting N2O emissions. The optimal LSTM model achieved a 36% improvement in mean absolute error (MAE), a 19% improvement in root mean squared error (RMSE), and a 6.92% improvement in R2 score compared to the RNN model. Additionally, LSTM models demonstrated better resilience to sudden changes in the target sequence, exhibiting a 9.54% higher percentage of explained variance compared to RNNs. These results highlight the potential of LSTM models for accurate and robust prediction of N2O emissions from wastewater treatment plants, contributing to effective greenhouse gas mitigation strategies.

Estimating the temporal and spatial distribution and threats of bisphenol A in temperate lakes using machine learning models

Bisphenol A (BPA) is easily enriched in many human-disturbed watersheds, particularly lakes with poor water mobility, which is posing a threat to aquatic biota. While previous studies have focused on the concentration of BPA in water and its toxicity to aquatic organisms, a small amount of measured data is not enough to reveal the temporal and spatial distribution and threats of BPA, and estimate the ecological risk in watersheds. Therefore, we collected 164 measured BPA data points from Taihu Lake to develop machine learning models using random forest (RF), support vector machine (SVM) and least square regression (LSR) and created month-by-month watershed prediction maps in temperate lakes to estimate the spatiotemporal distribution and threats of BPA. Due to RF's superior robustness to noisy data, the RF model exhibits the best performance among the three algorithms. The RF model showed acceptable predictive performance on the modeling dataset (coefficients of determination and root-mean-square error for the training set were 0.927 and 17.499, respectively, and 0.607, 39.645 for the validation set, respectively). The maps indicated that areas susceptible to anthropogenic activities were more severely polluted by BPA, and rainy climate may favor the migration of BPA to aquatic ecosystems. The model was also applied to predict 42 data points of BPA collected from Dianchi Lake, and the results showed that most predicted data were within a factor of 10 of the measured data, but the prediction accuracy of the model has declined. The ecological risks in the two lakes were evaluated and attention should be paid to the regions with higher risks. Our study provided a novel idea for comprehensive monitoring of an unconventional trace pollutant with endocrine disrupting effects in aquatic ecosystems and analyzing their spatiotemporal distribution, which will contribute to the scientific assessment of the ecological risk of BPA.

Predicting micropollutant fate during wastewater treatment using refined classical kinetic model based on quantitative monitoring in multi-metropolitan regions of South Korea

This study aimed to implement an extensive prediction model for the fate of micropollutants (MPs) in wastewater treatment plants (WWTPs). Five WWTPs equipped with seven different biological treatment processes were monitored from 2020 to 2022 with three to four sampling events in each year, and 27 datasets for 20 MPs were collected. Among these datasets, 12 were used to investigate the behavior and fate of MPs in WWTPs in South Korea. Metformin, acetaminophen, caffeine, naproxen, and ibuprofen were the MPs with the highest influent concentrations (ranging from 3,933.3-187,637.0 ng L-1) at all WWTPs. More than 90% of MPs were removed by biological treatment processes in all WWTPs. The Kruskal-Wallis test verified that their efficacy did not differ statistically (p-value > 0.05). Meanwhile, to refine the performance of the prediction model, this study optimized the biodegradation rate constants (kbio) of each MP according to the variation of seasonal water temperature. As a result, compared to the original prediction model, the mean difference between the actual data and predicted results (MEAN) decreased by 6.77%, while the Nash-Sutcliffe efficiency (NSE) increased by 0.226. The final MEAN and NSE for the refined prediction model were calculated to be 5.09% and 0.964, respectively. The prediction model made accurate predictions, even for MPs exhibiting behaviors different from other cases, such as estriol and atrazine. Consequently, the optimization strategy proposed in this study was determined to be effective because the overall removal efficiencies of MPs were successfully predicted even with limited reference datasets.

Combining chemical, bioanalytical and predictive tools to assess persistence, seasonality, and sporadic releases of organic micropollutants within the urban water cycle

Using a novel liquid chromatography-tandem mass spectrometry method with large volume direct injection and quantitation via isotope dilution, we evaluated the presence of 55 organic micropollutants in wastewater effluents, and locations within the Bow River and Elbow River watersheds in and around the city of Calgary, Alberta, Canada. In addition to establishing baseline micropollutant data for water utility operations, our study aimed to enhance our understanding of micropollutant behavior in the urban water cycle, assess the contributions of three wastewater treatment plants (WWTPs) to downstream receiving waters, explain the potential causes of total estrogenicity measured using the yeast-estrogen screen assay (YES), and prioritize a subset of substances for continuous monitoring. With data spanning 48 months and 95 river km, our results indicate the extensive persistence of metformin (antidiabetic), seasonality of N,N‑diethyl-m-toluamide (DEET, insect repellant), O-desmethylvenlafaxine (antidepressant metabolite), and sulfamethoxazole (antibiotic) in source waters, and sporadic detections of a well-known perfluoroalkyl substance (PFOA). The seasonality of pharmaceuticals at the sentinel downstream monitoring site appeared to coincide with river dilution while that of DEET was likely attributable to peak usage during the warmer months. Steroidal estrogens were rarely detected in wastewater effluents although total estrogenicity via YES was evident, suggesting the presence of less potent but more abundant non-steroidal estrogens (e.g., flame retardants, bisphenols, and phthalates). A conservative mass balance analysis suggests that the largest WWTP (serving a population of >1 million) consistently contributed the highest load of micropollutants, with the exception of metformin, which appeared to be influenced by a smaller WWTP (serving 115,000) that operates a different activated sludge process. We consider metformin, sucralose, diclofenac, and venlafaxine as more effective conservative tracers of wastewater pollution due to their notably higher concentrations and persistence in the Bow River compared to carbamazepine and caffeine, respectively. Finally, hierarchical clustering revealed a close association between E. coli and caffeine, supporting the use of caffeine as an indicator of short-term, untreated anthropogenic inputs. Overall, this study yields valuable insights on the presence, behavior, and sources of organic micropollutants in the urban water cycle and identifies indicators of anthropogenic impacts that are useful for prioritizing future monitoring campaigns in Calgary and elsewhere.

Prioritizing Pharmaceutical Contaminants in Great Lakes Tributaries Using Risk-Based Screening Techniques

In a study of 44 diverse sampling sites across 16 Great Lakes tributaries, 110 pharmaceuticals were detected of 257 monitored. The present study evaluated the ecological relevance of detected chemicals and identified heavily impacted areas to help inform resource managers and guide future investigations. Ten pharmaceuticals (caffeine, nicotine, albuterol, sulfamethoxazole, venlafaxine, acetaminophen, carbamazepine, gemfibrozil, metoprolol, and thiabendazole) were distinguished as having the greatest potential for biological effects based on comparison to screening-level benchmarks derived using information from two biological effects databases, the ECOTOX Knowledgebase and the ToxCast database. Available evidence did not suggest substantial concern for 75% of the monitored pharmaceuticals, including 147 undetected pharmaceuticals and 49 pharmaceuticals with screening-level alternative benchmarks. However, because of a lack of biological effects information, screening values were not available for 51 detected pharmaceuticals. Samples containing the greatest pharmaceutical concentrations and having the highest detection frequencies were from Lake Erie, southern Lake Michigan, and Lake Huron tributaries. Samples collected during low-flow periods had higher pharmaceutical concentrations than those collected during increased-flow periods. The wastewater-treatment plant effluent content in streams correlated positively with pharmaceutical concentrations. However, deviation from this correlation demonstrated that secondary factors, such as multiple pharmaceutical sources, were likely present at some sites. Further research could investigate high-priority pharmaceuticals as well as those for which alternative benchmarks could not be developed. Environ Toxicol Chem 2022;41:2221-2239. Published 2022. This article is a U.S. Government work and is in the public domain in the USA. Environmental Toxicology and Chemistry published by Wiley Periodicals LLC on behalf of SETAC.

A novel method for micropollutant quantification using deep learning and multi-objective optimization

Micropollutants (MPs) released into aquatic ecosystems have adverse effects on public health. Hence, monitoring and managing MPs in aquatic systems are imperative. MPs can be quantified by high-resolution mass spectrometry (HRMS) with stable isotope-labeled (SIL) standards. However, high cost of SIL solutions is a significant issue. This study aims to develop a rapid and cost-effective analytical approach to estimate MP concentrations in aquatic systems based on deep learning (DL) and multi-objective optimization. We hypothesized that internal standards could quantify the MP concentrations other than the target substance. Our approach considered the precision of intra-/inter-day repeatability and natural organic matter information to reduce instrumental error and matrix effect. We selected standard solutions to estimate the concentrations of 18 MPs. Among the optimal DL models, DarkNet-53 using nine standard solutions yielded the highest performance, while ResNet-50 yielded the lowest. Overall, this study demonstrated the capability of DL models for estimating MP concentrations.

Impacts of rapid urbanization on characteristics, sources and variation of fecal coliform at watershed scale

Microbial pollution is an environmental problem of growing concern for threatening human health. However, the impacts of rapid urbanization on characteristics, sources and variation of fecal coliform (FC) at watershed scale have not been fully explored. In this study, FC characteristics were monitored monthly for 2 years at 21 river sections in an urbanizing watershed, while the sources and continuously annual variation were quantified by integrating two commonly-used models. The results showed that FC varied from 10³ to 10⁶ MPN/L, indicating a great spatiotemporal variation at watershed scale. Peak FC occurred in summer and autumn among upstream and downstream areas, respectively. Besides, 65% impermeable surface was identified as the threshold of urban level, beyond which the key FC source would shift from agriculture to urban. It was also found that the changes of urban landscape patterns had poor correlation with annual variation of FC. In comparison, urbanization speed was identified as the major driver with the threshold of 30% for deteriorating FC pollution. The Low Impact Development could result in a 5.13%-97.59% reduction of FC at watershed scale.

Replacing the internal standard to estimate micropollutants using deep and machine learning

Similar to the worldwide proliferation of urbanization, micropollutants have been involved in aquatic and ecological environmental systems. These pollutants have the propensity to wreak havoc on human health and the ecological system; hence, it is important to persistently monitor micropollutants in the environment. Micropollutants are commonly quantified via target analysis using high resolution mass spectrometry and the stable isotope labeled (SIL) standard. However, the cost-intensiveness of this standard presents a major obstacle in measuring micropollutants. This study resolved this problem by developing data-driven models, including deep learning (DL) and machine learning (ML), to estimate the concentration of micropollutants without resorting to the SIL standard. Our study hypothesized that natural organic matter (NOM) could replace internal standards if there was a specific mass spectrum (MS) subset, including NOM information, which correlated with an SIL standard peak. Therefore, we analyzed the MS to find the specific MS subsets for replacing the SIL standard peak. Thirty-five alternative MS subsets were determined for applying DL and ML as input data. Thereafter, we trained four different DL models, namely, ResNet101, GoogLeNet, VGG16, and Inception v3, as well as three different ML models, i.e., random forest (RF), support vector machine (SVM), and artificial neural network (ANN). A total of 680 MS data were used for the model training to estimate five different micropollutants, namely Sulpiride, Metformin, and Benzotriazole. Among the DL models, ResNet 101 exhibited the highest model performance, showing that the average validation R² and MSE were 0.84 and 0.26 ng/L, respectively, while RF was the best in the ML models, manifesting R² and MSE values of 0.69 and 0.58 ng/L. The trained models showed accurate training and validation results for the estimation of the five micropollutant concentrations. Therefore, this study demonstrates that the suggested analysis has a potential for alternative micropollutant measurement that has rapid and economic vantages.

Organic Micropollutants in New York Lakes: A Statewide Citizen Science Occurrence Study

The widespread occurrence of organic micropollutants (OMPs) is a challenge for aquatic ecosystem management, and closing the gaps in risk assessment of OMPs requires a data-driven approach. One promising tool for increasing the spatiotemporal coverage of OMP data sets is through the active involvement of citizen volunteers to expand the scale of OMP monitoring. Working collaboratively with volunteers from the Citizens Statewide Lake Assessment Program (CSLAP), we conducted the first statewide study on OMP occurrence in surface waters of New York lakes. Samples collected by CSLAP volunteers were analyzed for OMPs by a suspect screening method based on mixed-mode solid-phase extraction and liquid chromatography-high resolution mass spectrometry. Sixty-five OMPs were confirmed and quantified in samples from 111 lakes across New York. Hierarchical clustering of OMP occurrence data revealed the relevance of 11 most frequently detected OMPs for classifying the contamination status of lakes. Partial least squares regression and multiple linear regression analyses prioritized three water quality parameters linked to agricultural and developed land uses (i.e., total dissolved nitrogen, specific conductance, and a wastewater-derived fluorescent organic matter component) as the best combination of predictors that partly explained the interlake variability in OMP occurrence. Lastly, the exposure-activity ratio approach identified the potential for biological effects associated with detected OMPs that warrant further biomonitoring studies. Overall, this work demonstrated the feasibility of incorporating citizen science approaches into the regional impact assessment of OMPs.

Spatiotemporal variability and key influencing factors of river fecal coliform within a typical complex watershed

Fecal coliform bacteria are a key indicator of human health risks; however, the spatiotemporal variability and key influencing factors of river fecal coliform have yet to be explored in a rural-suburban-urban watershed with multiple land uses. In this study, the fecal coliform concentrations in 21 river sections were monitored for 20 months, and 441 samples were analyzed. Multivariable regressions were used to evaluate the spatiotemporal dynamics of fecal coliform. The results showed that spatial differences were mainly dominated by urbanization level, and environmental factors could explain the temporal dynamics of fecal coliform in different urban patterns except in areas with high urbanization levels. Reducing suspended solids is a direct way to manage fecal coliform in the Beiyun River when the natural factors are difficulty to change, such as temperature and solar radiation. The export of fecal coliform from urban areas showed a quick and sensitive response to rainfall events and increased dozens of times in the short term. Landscape patterns, such as the fragmentation of impervious surfaces and the overall landscape, were identified as key factors influencing urban non-point source bacteria. The results obtained from this study will provide insight into the management of river fecal pollution.

Assessing Emissions from Pharmaceutical Manufacturing Based on Temporal High-Resolution Mass Spectrometry Data

This study presents a nontarget approach to detect discharges from pharmaceutical production in municipal wastewater treatment plant (WWTP) effluents and to estimate their relevance on the total emissions. Daily composite samples were collected for 3 months at two WWTPs in Switzerland, measured using liquid chromatography high-resolution mass spectrometry, and time series were generated for all features detected. The extent of intensity variation in the time series was used to differentiate relatively constant domestic inputs from highly fluctuating industrial emissions. We show that an intensity variation threshold of 10 correctly classifies compounds of known origin and reveals clear differences between the two WWTPs. At the WWTP receiving wastewater from a pharmaceutical manufacturing site, (i) 10 times as many potential industrial emissions were detected as compared to the WWTP receiving purely domestic wastewater; (ii) for 11 pharmaceuticals peak concentrations, >10 μg/L and up to 214 μg/L were quantified, which are clearly above typical municipal wastewater concentrations; and (iii) a pharmaceutical not authorized in Switzerland was identified. Signatures of potential industrial emissions were even traceable at the downstream Rhine monitoring station at a >4000-fold dilution. Several of them occurred repeatedly, suggesting that they were linked to regular production, not to accidents. Our results demonstrate that small wastewater volumes from a single industry not only left a clear signature in the effluents of the respective WWTP but also influenced the water quality of one of Europe's most important river systems. Overall, these findings indicate that pharmaceutical production is a relevant emission source even in highly developed countries with a strong focus on water quality, such as Switzerland.