Model for halo-acetic acids formation in bulk water of water supply systems

Exploring the potential of machine learning to understand the occurrence and health risks of haloacetic acids in a drinking water distribution system

Determining the occurrence of disinfection byproducts (DBPs) in drinking water distribution system (DWDS) remains challenging. Predicting DBPs using readily available water quality parameters can help to understand DBPs associated risks and capture the complex interrelationships between water quality and DBP occurrence. In this study, we collected drinking water samples from a distribution network throughout a year and measured the related water quality parameters (WQPs) and haloacetic acids (HAAs). 12 machine learning (ML) algorithms were evaluated. Random Forest (RF) achieved the best performance (i.e., R2 of 0.78 and RMSE of 7.74) for predicting HAAs concentration. Instead of using cytotoxicity or genotoxicity separately as the surrogate for evaluating toxicity associated with HAAs, we created a health risk index (HRI) that was calculated as the sum of cytotoxicity and genotoxicity of HAAs following the widely used Tic-Tox approach. Similarly, ML models were developed to predict the HRI, and RF model was found to perform the best, obtaining R2 of 0.69 and RMSE of 0.38. To further explore advanced ML approaches, we developed 3 models using uncertainty-based active learning. Our findings revealed that Categorical Boosting Regression (CAT) model developed through active learning substantially outperformed other models, achieving R2 of 0.87 and 0.82 for predicting concentration and the HRI, respectively. Feature importance analysis with the CAT model revealed that temperature, ions (e.g., chloride and nitrate), and DOC concentration in the distribution network had a significant impact on the occurrence of HAAs. Meanwhile, chloride ion, pH, ORP, and free chlorine were found as the most important features for HRI prediction. This study demonstrates that ML has the potential in the prediction of HAA occurrence and toxicity. By identifying key WQPs impacting HAA occurrence and toxicity, this research offers valuable insights for targeted DBP mitigation strategies.

The insightful water quality analysis and predictive model establishment via machine learning in dual-source drinking water distribution system

Dual-source drinking water distribution systems (DWDS) over single-source water supply systems are becoming more practical in providing water for megacities. However, the more complex water supply problems are also generated, especially at the hydraulic junction. Herein, we have sampled for a one-year and analyzed the water quality at the hydraulic junction of a dual-source DWDS. The results show that visible changes in drinking water quality, including turbidity, pH, UV254, DOC, residual chlorine, and trihalomethanes (TMHs), are observed at the sample point between 10 and 12 km to one drinking water plant. The average concentration of residual chlorine decreases from 0.74 ± 0.05 mg/L to 0.31 ± 0.11 mg/L during the water supplied from 0 to 10 km and then increases to 0.75 ± 0.05 mg/L at the end of 22 km. Whereas the THMs shows an opposite trend, the concentration reaches to a peak level at hydraulic junction area (10-12 km). According to parallel factor (PARAFAC) and high-performance size-exclusion chromatography (HPSEC) analysis, organic matters vary significantly during water distribution, and tryptophan-like substances and amino acids are closely related to the level of THMs. The hydraulic junction area is confirmed to be located at 10-12 km based on the water quality variation. Furthermore, data-driven models are established by machine learning (ML) with test R2 higher than 0.8 for THMs prediction. And the SHAP analysis explains the model results and identifies the positive (water temperature and water supply distance) and negative (residual chlorine and pH) key factors influencing the THMs formation. This study conducts a deep understanding of water quality at the hydraulic junction areas and establishes predictive models for THMs formation in dual-sources DWDS.

Analysis of the seasonal water quality variation at the hydraulic junction of a dual-source water distribution system

The implementation of a dual-source water supply system offers an increased level of reliability in water provision; however, intricate hydraulic dynamics introduce apprehensions regarding water safety at the hydraulic junction. In this study, we gathered data of the water quality at the hydraulic junction of a dual-source water supply system (plant A and plant B, sampling site A10 was near plant A, and sampling site A12 was near plant B) for one year in Suzhou Industrial Park. Our findings indicated that seasonal variations and water temperature exerted significant influence on the composition and formation of disinfection byproducts (DBPs). Notably, during the warmer months spanning from June to September, the concentration of trihalomethanes was the highest at the hydraulic junction, whereas the concentration of residual chloride was the lowest. The analysis on DBPs revealed that more Br-containing precursors in water in plant A resulted in the accumulation of more Br-containing DBPs at A10, whereas the highest concentration of Cl-containing DBPs accumulated at A12. The analysis of the dissolved organic matter (DOM) composition indicated an increase in concentration at A10 and A12 compared with that in plant A and plant B. The highest concentration of humic acids was observed at A10, whereas A12 accumulated the highest concentration of aromatic proteins and microbial metabolites. Owing to the fluctuations in water consumption patterns at the hydraulic junction, the water quality was susceptible to variability, thereby posing an elevated risk. Consequently, extensive efforts are warranted to ensure the maintenance of water safety and quality at this critical interface.

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.