Models for predicting carbonaceous disinfection by-products formation in drinking water treatment plants: a case study of South Korea

Application of artificial intelligence in (waste)water disinfection: Emphasizing the regulation of disinfection by-products formation and residues prediction

Water/wastewater ((waste)water) disinfection, as a critical process during drinking water or wastewater treatment, can simultaneously inactivate pathogens and remove emerging organic contaminants. Due to fluctuations of (waste)water quantity and quality during the disinfection process, conventional disinfection models cannot handle intricate nonlinear situations and provide immediate responses. Artificial intelligence (AI) techniques, which can capture complex variations and accurately predict/adjust outputs on time, exhibit excellent performance for (waste)water disinfection. In this review, AI application data within the disinfection domain were searched and analyzed using CiteSpace. Then, the application of AI in the (waste)water disinfection process was comprehensively reviewed, and in addition to conventional disinfection processes, novel disinfection processes were also examined. Then, the application of AI in disinfection by-products (DBPs) formation control and disinfection residues prediction was discussed, and unregulated DBPs were also examined. Current studies have suggested that among AI techniques, fuzzy logic-based neuro systems exhibit superior control performance in (waste)water disinfection, while single AI technology is insufficient to support their applications in full-scale (waste)water treatment plants. Thus, attention should be paid to the development of hybrid AI technologies, which can give full play to the characteristics of different AI technologies and achieve a more refined effectiveness. This review provides comprehensive information for an in-depth understanding of AI application in (waste)water disinfection and reducing undesirable risks caused by disinfection processes.

Pollution characteristics and health risk of sixty-five organics in one drinking water system: PAEs should be prioritized for control

Currently, a large number of emerging organic contaminants have been detected in domestic and international drinking water systems. However, there are differences among the research methods, which lead to system errors in directly comparing the hazards of different contaminants, so it is difficult to analyze the priority control pollutants and the risk control target in drinking water from previous studies. Therefore, we selected a drinking water treatment plant (DWTP) in the east of China, and detected trihalomethanes (THMs), antibiotics, phthalate esters (PAEs), organophosphate esters (OPEs), per and polyfluoroalkyl substances (PFASs), a total of sixty-five organic contaminants in one batch water sample of four seasons, and carried out the whole process monitoring of "Source water-DWTP-Network-Users", and calculated the health risks of contaminants in tap water. The results showed that DWTP could effectively remove antibiotics and PAEs; the removal rate of coagulation for antibiotics can be up to 47%; the release of PAEs in the plastic water supply pipe leads to a significant increase of the concentrations in the water transportation system, which can reach 2.92 times of that in finished water; compared with other contaminants, THMs and PAEs in tap water have higher health risks. This study reveals that THMs and PAEs are priority control organic pollutants, and the water supply network is the key risk control target in the drinking water system, providing a theoretical basis for how to ensure the safety of drinking water.

Microbial Risks Caused by Livestock Excrement: Current Research Status and Prospects

Livestock excrement is a major pollutant yielded from husbandry and it has been constantly imported into various related environments. Livestock excrement comprises a variety of microorganisms including certain units with health risks and these microorganisms are transferred synchronically during the management and utilization processes of livestock excrement. The livestock excrement microbiome is extensively affecting the microbiome of humans and the relevant environments and it could be altered by related environmental factors as well. The zoonotic microorganisms, extremely zoonotic pathogens, and antibiotic-resistant microorganisms are posing threats to human health and environmental safety. In this review, we highlight the main feature of the microbiome of livestock excrement and elucidate the composition and structure of the repertoire of microbes, how these microbes transfer from different spots, and they then affect the microbiomes of related habitants as a whole. Overall, the environmental problems caused by the microbiome of livestock excrement and the potential risks it may cause are summarized from the microbial perspective and the strategies for prediction, prevention, and management are discussed so as to provide a reference for further studies regarding potential microbial risks of livestock excrement microbes.

Appraisal of machine learning techniques for predicting emerging disinfection byproducts in small water distribution networks

Monitoring emerging disinfection byproducts (DBPs) is challenging for many small water distribution networks (SWDNs), and machine learning-based predictive modeling could be an alternative solution. In this study, eleven machine learning techniques, including three multivariate linear regression-based, three regression tree-based, three neural networks-based, and two advanced non-parametric regression techniques, are used to develop models for predicting three emerging DBPs (dichloroacetonitrile, chloropicrin, and trichloropropanone) in SWDNs. Predictors of the models include commonly-measured water quality parameters and two conventional DBP groups. Sampling data of 141 cases were collected from eleven SWDNs in Canada, in which 70 % were randomly selected for model training and the rest were used for validation. The modeling process was reiterated 1000 times for each model. The results show that models developed using advanced regression techniques, including support vector regression and Gaussian process regression, exhibited the best prediction performance. Support vector regression models showed the highest prediction accuracy (R² =0.94) and stability for predicting dichloroacetonitrile and trichloropropanone, and Gaussian process regression models are optimal for predicting chloropicrin (R² =0.92). The difference is likely due to the much lower concentrations of chloropicrin than dichloroacetonitrile and trichloropropanone. Advanced non-parametric regression techniques, characterized by a probabilistic nature, were identified as most suitable for developing the predictive models, followed by neural network-based (e.g., generalized regression neural network), regression tree-based (e.g., random forest), and multivariate linear regression-based techniques. This study identifies promising machine learning techniques among many commonly-used alternatives for monitoring emerging DBPs in SWDNs under data constraints.

Modeling the formation of trihalomethanes in rural and semi-urban drinking water distribution networks of Costa Rica

Chlorination is one of the most important stages in the treatment of drinking water due to its effectiveness in the inactivation of pathogenic organisms. However, the reaction between chlorine and natural organic matter (NOM) generates harmful disinfection by-products (DBPs), such as trihalomethanes (THMs). In this research, drinking water quality data was collected from the distribution networks of 19 rural and semi-urban systems that use water sources as springs, surfaces, and a mixture of both, in three provinces of Costa Rica from April 2018 to September 2019. Twelve models were developed from four data sets: all water sources, spring, surface, and a mixture of spring and surface waters. Linear, logarithmic, and exponential multivariate regression models were developed for each data set to predict the concentration of total trihalomethanes (TTHMs) in the distribution networks. Concentrations of TTHMs were found between < 0.20 and 91.31 µg/L, with chloroform being the dominant species accounting for 62% of TTHMs on average. Turbidity, free residual chlorine, total organic carbon (TOC), dissolved organic carbon (DOC), and ultraviolet absorbance at 254 nm (UV₂₅₄) showed a significant correlation with TTHMs. In all the data sets the linear models presented the best goodness-of-fit and were moderately robust. Four models, the best of each data set, were validated with data from the same systems, and, according to the criteria of R², standard error (SE), mean square error (MSE), and mean absolute error (MAE), spring water and mixed spring/surface water models showed a satisfactory level of explanation of the variability of the data. Moreover, the models seem to better predict TTHM concentrations below 30 µg/L. These models were satisfactory and could be useful for decision-making in drinking water supply systems.

Using simple and easy water quality parameters to predict trihalomethane occurrence in tap water

Monitoring of disinfection by-products (DBPs) in water supply system is important to ensure safety of drinking water. Yet it is a laborious job. Developing predictive DBPs models using simple and easy parameters is a promising way. Yet current models could not be well applied into practice because of the improper dataset (e.g. not from real tap water) they used or involving the parameters that are difficult to measure or require expensive instruments. In this study, four simple and easy water quality parameters (temperature, pH, UVA₂₅₄ and Cl₂) were used to predict trihalomethane (THMs) occurrence in tap water. Linear/log linear regression models (LRM) and radial basis function artificial neural network (RBF ANN) were adopted to develop the THMs models. 64 observations from tap water samples were used to develop and test models. Results showed that only one or two parameters entered LRMs, and their prediction ability was very limited (testing datasets: N₂₅ = 46-69%, r_p = 0.334-0.459). Different from LRM, the prediction accuracy of RBF ANNs developed with pH, temperature, UVA₂₅₄ and Cl₂ can be improved continuously by tweaking the maximum number of neuron (MN) and Gaussian function spread (S) until it reached best. The optimum RBF ANNs of T-THMs, TCM and BDCM were obtained when setting MN = 20, S = 100, 100.1 and 60, respectively, where the N₂₅ and r_p values for testing datasets reached 85-92% and 0.813-0.886, respectively. Accurate predictions of THMs by RBF ANNs with these four simple and easy parameters paved an economic and convenient way for THMs monitoring in real water supply system.

Assessing the efficacy of dissolved air and flash-pressurized flotations using low energy for the removal of organic precursors and disinfection byproducts: a pilot-scale study

Dissolved air flotation (DAF) is a widely used treatment process in drinking water and wastewater treatment plants despite high energy cost associated with operation and maintenance (accounts 50% of the total annual operation cost). In recent years, the focus has been diverted to optimizing or reducing energy, and a microbubble generation without a saturator was developed and used in small treatment facilities because of its simple structure. Thus, in this study, DAF and low-energy flash-pressurized flotation (FPF) efficacies were investigated in a pilot plant based on organic precursors, different molecular weight (MW) fractions, and disinfection byproduct reduction. The organic fractions with different MW was analyzed by liquid chromatography-organic carbon detector. Both DAF (550 kPa) and FPF (300 kPa) showed similar removal of dissolved organic carbon (DOC) and chromatographic DOC; however, the removal tendency of different MW fractions found was different. There was no significant difference in the removal of biopolymers, building blocks, and low molecular weight (LMW) neutrals for both DAF and FPF. Interestingly, the removal of LMW acids was found to be higher (93.8%) for DAF, whereas only 35.8% removal was observed for FPF. The total trihalomethanes concentration in a DAF-treated water sample was found to be 10% lower than that of FPF. Also, the reduction in haloacetonitriles was found to be slightly higher for a water sample treated by using DAF than by using FPF (1.5 and 1.8 μg L^-1, respectively). Moreover, the formation of chloral hydrate was observed to be the same (1.9 μg L^-1) for DAF- and FPF-treated water, with a total reduction of 40.6%. FPF with low pressure enabled a reduction in energy of around 55% when compared with DAF. Thus, FPF with low-pressure energy provides an alternative to DAF by reducing the annual operation cost and carbon footprint.

New methods based on back propagation (BP) and radial basis function (RBF) artificial neural networks (ANNs) for predicting the occurrence of haloketones in tap water

Haloketones (HKs) is one class of disinfection by-products (DBPs) which is genetically toxic and mutagenic. Monitoring HKs in drinking water is important for drinking water safety, yet it is a time-consuming and laborious job. Developing predictive models of HKs to estimate their occurrence in drinking water is a good alternative, but to date no study was available for HKs modeling. This study was to explore the feasibility of linear, log linear regression models, back propagation (BP) as well as radial basis function (RBF) artificial neural networks (ANNs) for predicting HKs occurrence (including dichloropropanone, trichloropropanone and total HKs) in real water supply systems. Results showed that the overall prediction ability of RBF and BP ANNs was better than linear/log linear models. Though the BP ANN showed excellent prediction performance in internal validation (N₂₅ = 98-100%, R² = 0.99-1.00), it could not well predict HKs occurrence in external validation (N₂₅ = 62-69%, R² = 0.202-0.848). Prediction ability of RBF ANN in external validation (N₂₅ = 85%, R² = 0.692-0.909) was quite good, which was comparable to that in internal validation (N₂₅ = 74-88%, R² = 0.799-0.870). These results demonstrated RBF ANN could well recognized the complex nonlinear relationship between HKs occurrence and the related water quality, and paved a new way for HKs prediction and monitoring in practice.