Machine-learning insights into nitrate-reducing communities in a full-scale municipal wastewater treatment plant

A metagenome-derived artificial intelligence modeling framework advances the predictive diagnosis and interpretation of petroleum-polluted groundwater

Groundwater (GW) quality monitoring is vital for sustainable water resource management. The present study introduced a metagenome-derived machine learning (ML) model aimed at enhancing the predictive understanding and diagnostic interpretation of GW pollution associated with petroleum. In this framework, taxonomic and metabolic profiles derived from GW metagenomes were combined for use as the input dataset. By employing strategies that optimized data integration, model selection, and parameter tuning, we achieved a significant increase in diagnostic accuracy for petroleum-polluted GW. Explanatory artificial intelligence techniques identified petroleum degradation pathways and Rhodocyclaceae as strong predictors of a pollution diagnosis. Metagenomic analysis corroborated the presence of gene operons encoding aminobenzoate and xylene biodegradation within the de novo assembled genome of Rhodocyclaceae. Our genome-centric metagenomic analysis thus clarified the ecological interactions associated with microbiomes in breaking down petroleum contaminants, validating the ML-based diagnostic results. This metagenome-derived ML framework not only enhances the predictive diagnosis of petroleum pollution but also offers interpretable insights into the interaction between microbiomes and petroleum. The proposed ML framework demonstrates great promise for use as a science-based strategy for the on-site monitoring and remediation of GW pollution.

Wastewater treatment process enhancement based on multi-objective optimization and interpretable machine learning

Optimization and control of wastewater treatment process (WTP) can contribute to cost reduction and efficiency. A wastewater treatment process multi-objective optimization (WTPMO) framework is proposed in this paper to provide suggestions for decision-making in setting parameters of WTP. Firstly, the prediction models based on Extreme Gradient Boosting (XGB) with Bayesian optimization (BO) are developed for predicting effluent water quality (EQ) and energy consumption (EC) for different influent quality and process parameter settings. Then, the SHapley Additive exPlanations (SHAP) algorithm is used to complement the interpretability of machine learning to quantitatively evaluate the impact of different features on the predicted targets. Finally, the Non-dominated Sorting Genetic Algorithm II (NSGA-II) with the Technique for Ordering Preferences on Similarity of Ideal Solutions (TOPSIS) is introduced to solve and make decisions on the multi-objective optimization problem. The WTPMO applicability is validated on Benchmark Simulation Model 1 (BSM1). The results show that BOXGB achieves accurate prediction for EQ and EC with R2 values of 0.923 and 0.965, respectively, indicating that BO can effectively select the model hyperparameters in XGB. Based on SHAP supplemented the interpretability of the model to fully explain how the influent water quality and decision variables affect the EQ and EC of the WTP. In addition, the optimized process parameters are determined based on NSGA-II and TOPSIS, and the EC optimization rate is 1.552% while guaranteeing water quality compliance. Overall, this research can effectively achieve the optimization of WTP, ensure that the effluent water quality meets the standards while reducing energy consumption, assist Wastewater treatment plants (WWTPs) to achieve more intelligent and efficient operation and maintenance management, and provide strong support for environmental protection and sustainable development goals.

Multi-approach assessment of groundwater biogeochemistry: Implications for the site characterization of prospective spent nuclear fuel repository sites

The disposal of spent nuclear fuel in deep subsurface repositories using multi-barrier systems is considered to be the most promising method for preventing radionuclide leakage. However, the stability of the barriers can be affected by the activities of diverse microbes in subsurface environments. Therefore, this study investigated groundwater geochemistry and microbial populations, activities, and community structures at three potential spent nuclear fuel repository construction sites. The microbial analysis involved a multi-approach including both culture-dependent, culture-independent, and sequence-based methods for a comprehensive understanding of groundwater biogeochemistry. The results from all three sites showed that geochemical properties were closely related to microbial population and activities. Total number of cells estimates were strongly correlated to high dissolved organic carbon; while the ratio of adenosine-triphosphate:total number of cells indicated substantial activities of sulfate reducing bacteria. The 16S rRNA gene sequencing revealed that the microbial communities differed across the three sites, with each featuring microbes performing distinctive functions. In addition, our multi-approach provided some intriguing findings: a site with a low relative abundance of sulfate reducing bacteria based on the 16S rRNA gene sequencing showed high populations during most probable number incubation, implying that despite their low abundance, sulfate reducing bacteria still played an important role in sulfate reduction within the groundwater. Moreover, a redundancy analysis indicated a significant correlation between uranium concentrations and microbial community compositions, which suggests a potential impact of uranium on microbial community. These findings together highlight the importance of multi-methodological assessments in better characterizing groundwater biogeochemical properties for the selection of potential spent nuclear fuel disposal sites.

Side effects of the addition of an adsorbent for the nitrification performance of a microbiome in the treatment of an antibiotic mixture

This work determined the effect of biochar (BC) as an adsorbent on the nitrifying microbiome in regulating the removal, transformation, fate, toxicity, and potential environmental consequences of an antibiotic mixture containing oxytetracycline (OTC) and sulfamethoxazole (SMX). Despite the beneficial role of BC as reported in the literature, the present study revealed side effects for the nitrifying microbiome and its functioning arising from the presence of BC. Long-term monitoring revealed severe disruption to nitratation via the inhibition of both nitrite oxidizers (e.g., Nitrospira defluvii) and potential comammox species (e.g., Ca. Nitrospira nitrificans). Byproducts (BPs) more toxic than the parent compounds were found to persist at a high relative abundance, particularly in the presence of BC. Quantitative structure-activity relationship modeling determined that the physicochemical properties of the toxic BPs significantly differed from those of OTC and SMX. The results suggested that the BPs tended to mobilize and accumulate on the surface of the solids in the system (i.e., the BC and biofilm), disrupting the nitrifiers growing at the interface. Collectively, this study provides novel insights, demonstrating that the addition of adsorbents to biological systems may not necessarily be beneficial; rather, they may generate side effects for specific bacteria that have important ecosystem functions.

Environmental consequences of transformation products from an antibiotic mixture and their mitigation in a wastewater microbiome using an HCl-modified adsorbent

This study enhanced our understanding of antibiotic mixtures' occurrence, transformation, toxicity, and ecological risks. The role of acid-modified biochar (BC) in treating antibiotic residues was explored, shedding light on how BC influences the fate, mobility, and environmental impact of antibiotics and transformation products (TPs) in an activated sludge (AS) microbiome. A mixture of oxytetracycline and sulfamethoxazole was found to synergistically (or additively) inhibit cell growth of AS and disrupt the microbiome structure, species richness/diversity, and function. The formation of TPs with potentially higher toxicity and persistence than the original compounds was identified, explaining the microbiome disruption. Agricultural waste-derived BC was optimized for contaminant adsorption, leading to a reduction in toxicity when added to AS by sequestering TPs on its surface. This work highlighted adsorbents as a practical engineering strategy for mitigating liquid-phase contaminants' toxicological consequences, proactively controlling the fate and effects of antibiotics and TPs.

Enhancing effluent quality prediction in wastewater treatment plants through the integration of factor analysis and machine learning

Precisely predicting the concentration of nitrogen-based pollutants from the wastewater treatment plants (WWTPs) remains a challenging yet crucial task for optimizing operational adjustments in WWTPs. In this study, an integrated approach using factor analysis (FA) and machine learning (ML) models was employed to accurately predict effluent total nitrogen (Ntoteff) and nitrate nitrogen (NO3-Neff) concentrations of the WWTP. The input values for the ML models were honed through FA to optimize factors, thereby significantly enhancing the ML prediction accuracy. The prediction model achieved a highest coefficient of determination (R2) of 97.43 % (Ntoteff) and 99.38 % (NO3-Neff), demonstrating satisfactory generalization ability for predictions up to three days ahead (R2 >80 %). Moreover, the interpretability analysis identified that the denitrification factor, the pollutant load factor, and the meteorological factor were significant. The model framework proposed in this study provides a valuable reference for optimizing the operation and management of wastewater treatment.

How to Provide Nitrite Robustly for Anaerobic Ammonium Oxidation in Mainstream Nitrogen Removal

Innovation in decarbonizing wastewater treatment is urgent in response to global climate change. The practical implementation of anaerobic ammonium oxidation (anammox) treating domestic wastewater is the key to reconciling carbon-neutral management of wastewater treatment with sustainable development. Nitrite availability is the prerequisite of the anammox reaction, but how to achieve robust nitrite supply and accumulation for mainstream systems remains elusive. This work presents a state-of-the-art review on the recent advances in nitrite supply for mainstream anammox, paying special attention to available pathways (forward-going (from ammonium to nitrite) and backward-going (from nitrate to nitrite)), key controlling strategies, and physiological and ecological characteristics of functional microorganisms involved in nitrite supply. First, we comprehensively assessed the mainstream nitrite-oxidizing bacteria control methods, outlining that these technologies are transitioning to technologies possessing multiple selective pressures (such as intermittent aeration and membrane-aerated biological reactor), integrating side stream treatment (such as free ammonia/free nitrous acid suppression in recirculated sludge treatment), and maintaining high activity of ammonia-oxidizing bacteria and anammox bacteria for competing oxygen and nitrite with nitrite-oxidizing bacteria. We then highlight emerging strategies of nitrite supply, including the nitrite production driven by novel ammonia-oxidizing microbes (ammonia-oxidizing archaea and complete ammonia oxidation bacteria) and nitrate reduction pathways (partial denitrification and nitrate-dependent anaerobic methane oxidation). The resources requirement of different mainstream nitrite supply pathways is analyzed, and a hybrid nitrite supply pathway by combining partial nitrification and nitrate reduction is encouraged. Moreover, data-driven modeling of a mainstream nitrite supply process as well as proactive microbiome management is proposed in the hope of achieving mainstream nitrite supply in practical application. Finally, the existing challenges and further perspectives are highlighted, i.e., investigation of nitrite-supplying bacteria, the scaling-up of hybrid nitrite supply technologies from laboratory to practical implementation under real conditions, and the data-driven management for the stable performance of mainstream nitrite supply. The fundamental insights in this review aim to inspire and advance our understanding about how to provide nitrite robustly for mainstream anammox and shed light on important obstacles warranting further settlement.

Reclaimed water influences bacterioplankton and bacteriobenthos communities differently in river networks

Reclaimed water reuse is a promising strategy for addressing water scarcity; however, its potential ecological impact remains largely unknown. In particular, the differential effects of reclaimed water on microbial communities in various habitats remain poorly understood. Here, we aimed to elucidate the distinct effects of reclaimed water on bacterioplankton and bacteriobenthos communities in reclaimed water-receiving river networks from multiple perspectives, including community structure, co-occurrence patterns, assembly mechanisms, and nitrogen cycle function. Significant differences in microbial composition were observed between the plankton and benthic habitats, and the average numbers of amplicon sequence variants (ASVs) that originated from the wastewater treatment plants (WWTP) sites were 310.0 and 613.3, respectively, indicating a stronger association between WWTP and benthic habitats. Random forest and network co-occurrence analyses identified the genus Clostridium_sensu_stricto as a biomarker and key module hub. The assembly of bacteriobenthos communities was driven primarily by deterministic processes (58.74% for River-S and 58.94% for WWTP-S), whereas for bacterioplankton communities, this proportion was reduced to 18.02% (River-W) and 19.09% (WWTP-W). The qPCR revealed a large difference in abundance between the N cycling related genes of bacteriobenthos (average 2.47 × 106 copies/ng) and bacterioplankton (average 3.11 × 103 copies/ng) communities, and different interaction patterns with functional genes. Variance partitioning analysis (VPA) indicated that nitrogen was the most important pollutant, affecting the structure and ecological functions of microbial communities. Moreover, pathway analysis suggested that the reuse of reclaimed water may have enhanced the N-cycling functions of microbial communities and the emission of nitrous oxide.

Artificial intelligence in wastewater treatment: A data-driven analysis of status and trends

Wastewater treatment is a complex process that involves many uncertainties, leading to fluctuations in effluent quality and costs, and environmental risks. Artificial intelligence (AI) can handle complex nonlinear problems and has become a powerful tool for exploring and managing wastewater treatment systems. This study provides a summary of the current status and trends in AI research as applied to wastewater treatment, based on published papers and patents. Our results indicate that, at present, AI is primarily used to evaluate removal of pollutants (conventional, typical, and emerging contaminants), optimize models and process parameters, and control membrane fouling. Future research will likely continue to focus on removal of phosphorus, organic pollutants, and emerging contaminants. Moreover, analyzing microbial community dynamics and achieving multi-objective optimization are promising directions of research. The knowledge map shows that there may be future technological innovation related to predicting water quality under specific conditions, integrating AI with other information technologies and utilizing image-based AI and other algorithms in wastewater treatment. In addition, we briefly review development of artificial neural networks (ANNs) and explore the evolutionary path of AI in wastewater treatment. Our findings provide valuable insights into potential opportunities and challenges for researchers applying AI to wastewater treatment.

A gravity-driven membrane bioreactor in treating the real decentralized domestic wastewater: Flux stability and membrane fouling

Domestic wastewater in decentralized sites is capturing increasing attention. However, conventional treatment technology is not sufficiently cost-effective. In this study, real domestic wastewater was treated directly using a gravity-driven membrane bioreactor (GDMBR) at 45 mbar without backwashing or chemical cleaning, and the effects of different membrane pore sizes (0.22 μm, 0.45 μm, and 150 kDa) on flux development and contaminants removal were examined. The results showed that the flux initially decreased and then stabilized throughout long-term filtration and that the stabilized flux level of the GDMBR equipped the membranes with the pore size of 150 kDa and 0.22 μm was higher than that of 0.45 μm membrane and was in the range of 3.25-4.25 L m^-2h^-1. The flux stability was related to spongelike and permeable biofilm generation on the membrane surface in the GDMBR system. The presence of aeration shear on the membrane surface would cause the slough off of biofilm from the membrane surface, especially in the scenarios of GDMBR with the membrane pore size of 150 kDa and 0.22 μm, contributing to lower accumulation of extracellular polymeric substance (EPS) and smaller biofilm thickness compared to that of 0.45 μm membrane. Furthermore, the GDMBR system achieved efficient removals of chemical oxygen demand (COD), and ammonia, with average removal efficiencies of 60-80% and 70%. The high biological activity and microbial community diversity within the biofilm would improve its biodegradation and should be responsible for the efficient removal performance of contaminants. Interestingly, the membrane effluent could effectively retain total nitrogen (TN) and total phosphorus (TP). Therefore, it's feasible to adopt the GDMBR process to treat the actual domestic wastewater in the decentralized locations, and these findings could be expected to develop some simple and environmentally friendly strategies for decentralized wastewater treatment with fewer inputs.

Machine learning reveals the complex ecological interplay of microbiome in a full-scale membrane bioreactor wastewater treatment plant

Membrane bioreactor (MBR) systems are one of the most widely used wastewater treatment processes for various municipal and industrial waste streams. The present study aimed to advance the understanding of ecologically important keystone taxa that play an important role in full-scale MBR systems. A machine-learning (ML) modeling framework based on microbiome data was developed to successfully predict, with an average accuracy of >91.6%, the operational characteristics of three representative full-scale wastewater systems: an MBR, a conventional activated sludge system, and a sequencing batch reactor. ML-based feature-importance analysis identified Ferruginibacter as a keystone organism in the MBR system. The phylogeny and known ecophysiology of members of Ferruginibacter supported their role in metabolizing complex organic polymers (e.g., extracellular polymeric substances) in MBR systems characterized by high concentrations of mixed liquor suspended solids and a high solid retention time. ML regression modeling also revealed temporal patterns of Ferruginibacter in response to water temperature. ML modeling was thus successfully employed in the present study to investigate complex/non-linear relationships between keystone taxa and environmental conditions that cannot be detected using conventional approaches. Overall, our microbiome-data-enabled ML modeling approach represents a methodological advance for identifying keystone taxa and their complex ecological interactions, which has implications for the sustainable and predictive management of MBR systems.

The Role of Conventional Methods and Artificial Intelligence in the Wastewater Treatment: A Comprehensive Review

Water pollution is a severe health concern. Several studies have recently demonstrated the efficacy of various approaches for treating wastewater from anthropogenic activities. Wastewater treatment is an artificial procedure that removes contaminants and impurities from wastewater or sewage before discharging the effluent back into the environment. It can also be recycled by being further treated or polished to provide safe quality water for use, such as potable water. Municipal and industrial wastewater treatment systems are designed to create effluent discharged to the surrounding environments and must comply with various authorities’ environmental discharge quality rules. An effective, low-cost, environmentally friendly, and long-term wastewater treatment system is critical to protecting our unique and finite water supplies. Moreover, this paper discusses water pollution classification and the three traditional treatment methods of precipitation/encapsulation, adsorption, and membrane technologies, such as electrodialysis, nanofiltration, reverse osmosis, and other artificial intelligence technology. The treatment performances in terms of application and variables have been fully addressed. The ultimate purpose of wastewater treatment is to protect the environment that is compatible with public health and socioeconomic considerations. Realization of the nature of wastewater is the guiding concept for designing a practical and advanced treatment technology to assure the treated wastewater’s productivity, safety, and quality.

Effects of biochar addition on the fate of ciprofloxacin and its associated antibiotic tolerance in an activated sludge microbiome

This study investigated the effects of adding biochar (BC) on the fate of ciprofloxacin (CIP) and its related antibiotic tolerance (AT) in activated sludge. Three activated sludge reactors were established with different types of BC, derived from apple, pear, and mulberry tree, respectively, and one reactor with no BC. All reactors were exposed to an environmentally relevant level of CIP that acted as a definitive selective pressure significantly promoting AT to four representative antibiotics (CIP, ampicillin, tetracycline, and polymyxin B) by up to two orders of magnitude. While CIP removal was negligible in the reactor without BC, the BC-dosed reactors effectively removed CIP (70-95% removals) through primarily adsorption by BC and biodegradation/biosorption by biomass. The AT in the BC-added reactors was suppressed by 10-99%, compared to that without BC. The BC addition played a key role in sequestering CIP, thereby decreasing the selective pressure that enabled the proactive prevention of AT increase. 16S rRNA gene sequencing analysis showed that the BC addition alleviated the CIP-mediated toxicity to community diversity and organisms related to phosphorous removal. Machine learning modeling with random forest and support vector models using AS microbiome data collectively pinpointed Achromobacter selected by CIP and strongly associated with the AT increase in activated sludge. The identification of Achromobacter as an important AT bacteria revealed by the machine learning modeling with multiple models was also validated with a linear Pearson's correlation analysis. Overall, our study highlighted Achromobacter as a potential useful sentinel for monitoring AT occurring in the environment and suggested BC as a promising additive in wastewater treatment to improve micropollutant removal, mitigate potential AT propagation, and maintain community diversity against toxic antibiotic loadings.

Interfacing Machine Learning and Microbial Omics: A Promising Means to Address Environmental Challenges

Microbial communities are ubiquitous and carry an exceptionally broad metabolic capability. Upon environmental perturbation, microbes are also amongst the first natural responsive elements with perturbation-specific cues and markers. These communities are thereby uniquely positioned to inform on the status of environmental conditions. The advent of microbial omics has led to an unprecedented volume of complex microbiological data sets. Importantly, these data sets are rich in biological information with potential for predictive environmental classification and forecasting. However, the patterns in this information are often hidden amongst the inherent complexity of the data. There has been a continued rise in the development and adoption of machine learning (ML) and deep learning architectures for solving research challenges of this sort. Indeed, the interface between molecular microbial ecology and artificial intelligence (AI) appears to show considerable potential for significantly advancing environmental monitoring and management practices through their application. Here, we provide a primer for ML, highlight the notion of retaining biological sample information for supervised ML, discuss workflow considerations, and review the state of the art of the exciting, yet nascent, interdisciplinary field of ML-driven microbial ecology. Current limitations in this sphere of research are also addressed to frame a forward-looking perspective toward the realization of what we anticipate will become a pivotal toolkit for addressing environmental monitoring and management challenges in the years ahead.

A Classification-Based Machine Learning Approach to the Prediction of Cyanobacterial Blooms in Chilgok Weir, South Korea

Cyanobacterial blooms appear by complex causes such as water quality, climate, and hydrological factors. This study aims to present the machine learning models to predict occurrences of these complicated cyanobacterial blooms efficiently and effectively. The dataset was classified into groups consisting of two, three, or four classes based on cyanobacterial cell density after a week, which was used as the target variable. We developed 96 machine learning models for Chilgok weir using four classification algorithms: k-Nearest Neighbor, Decision Tree, Logistic Regression, and Support Vector Machine. In the modeling methodology, we first selected input features by applying ANOVA (Analysis of Variance) and solving a multi-collinearity problem as a process of feature selection, which is a method of removing irrelevant features to a target variable. Next, we adopted an oversampling method to resolve the problem of having an imbalanced dataset. Consequently, the best performance was achieved for models using datasets divided into two classes, with an accuracy of 80% or more. Comparatively, we confirmed low accuracy of approximately 60% for models using datasets divided into three classes. Moreover, while we produced models with overall high accuracy when using logCyano (logarithm of cyanobacterial cell density) as a feature, several models in combination with air temperature and NO3-N (nitrate nitrogen) using two classes also demonstrated more than 80% accuracy. It can be concluded that it is possible to develop very accurate classification-based machine learning models with two features related to cyanobacterial blooms. This proved that we could make efficient and effective models with a low number of inputs.

Simultaneous phosphorus and nitrogen removal with different C/N ratios in a low oxygen aeration system: Microorganisms and mechanisms

In this study, a combined system with simultaneous nitrification, denitrification, and phosphorus removal was operated in continuous low oxygen aeration mode, and the effect of lower oxygen aeration (dissolved oxygen [DO] 0.5-1.5 mg/L) on its performance was examined. The combined system consisted of sludge and high-efficiency biological packing and was operated using four carbon/nitrogen ratios (C/N) with being 10:1, 8:1, 6:1, 10:1. Experimental results showed that the combined system could perform an efficient nitrogen and phosphorus removal under low DO and C/N ratio of 8:1 condition, and removal efficiencies of chemical oxygen demand (COD), NH₄ ⁺ -N, and PO₄ ^3- -P were 80.01%, 99.03%, and 89.51%, respectively. High-throughput analysis indicated that the functional species of denitrifying bacteria, including Ferruginibacter Azospira, Comamonas, Bacilli, Hyphomicrobium, Thauera, and Comamonadaceae, were important participants in biological nutrient removal. Meanwhile, Acinetobacter was enriched in the combined system, which contributed to phosphorus removal. PRACTITIONER POINTS: A combined system was operated firstly under continuous low oxygen condition. The lower dissolved oxygen (DO) of the combined system was maintained at 0.50-1.5 mg/L level. The combined system could realize simultaneous phosphorus and nitrogen removal under C/N ratio of 8:1. Several functional bacteria were enriched in the coupled systems.