Trihalomethanes Prediction Research Articles

Applied gradient boosting decision tree algorithms for accurate prediction of trihalomethanes: A case study in dual-sources drinking water distribution system in metropolitan

The complex hydraulic environment in dual-source drinking water distribution system (DWDS) in metropolitan puts water safety in an unknown situation, which requires systematic water quality monitoring and controlling to reduce the water risk during water distribution process. Given that, this study conducted a one-year sampling of trihalomethanes (THMs) and identified the hydraulic junction area in a real dual-source DWDS. For efficient prediction of THMs, several predictive frameworks were established via mechanistic algorithms and machine learning (ML). The results indicated that Gradient Boosting Decision Tree (GBDT) algorithm achieved higher interpretability and generalizability in describing the relationship between various of features with R2 reaching 0.903, 0.908, 0.945 and 0.959 for trichloromethane (TCM), bromodichloromethane (BDCM), dibromomonochloromethane (DBCM) and tribromomethane (TBM), respectively. Shapley additive explanations (SHAP) analysis of GBDT models further identified water temperature, residual chlorine, water supply distance, and pH were key features affecting THMs formation in practical DWDS. Furthermore, the spatio-temporal distribution of THMs was simulated by GBDT models and identified the region might be exposed to high risk of the THMs. The simulation results indicated that the DBCM and TBM were more likely to form in the region nearly to DWTP-X, whereas in the region nearly to DWTP-Y, the TCM and BDCM were the dominant THMs species due to differences in raw water characteristics. Undoubtedly, this study provided novel insights into utilizing ML models to predict THMs levels in dual-source DWDS in the metropolitan.

Simultaneous prediction of trihalomethanes, haloacetic acids, haloacetonitriles and haloacetamides using simulated distribution system tests

This study analysed the spatial and temporal occurrence of 29 disinfection by-products (DBPs) formed by chlorination and chloramination.

Modeling and prediction of trihalomethanes in the drinking water treatment plant of Thessaloniki, Greece

A matter of major importance relies on managing the water treatment process in order to optimize the disinfection process and the corresponding cost, maintaining the high standards of the produced water. The paper aims at developing a prediction model for trihalomethanes formation of the water treatment plant of Thessaloniki (Northern Greece) by means of a set of explanatory variables such as temperature, pH, turbidity, total organic carbon, chlorine dose and residence time. The dataset runs from 2008 to 2020. The analysis used a set of advanced statistical techniques (One-way Anova, Tukey Pairwise Comparisons) as well as a combination of adequate statistical methods such as Partial Least Square regression (PLS), Multiple Linear Regression (MLR) and Stepwise Regression. The results revealed a strong positive correlation of temperature with concentrations of trihalomethanes. After validation, the best model was the one of stepwise regression that included only temperature and residence time to predict total trihalomethanes with high accuracy at low and medium concentration levels (R2 = 46.07%, R2pred = 42.9%).

Prediction of Trihalomethanes in water supply of Chattogram city by empirical models and cancer risk through multi-pathway exposure

This study predicts the possible occurrence of trihalomethanes (THMs) in water supply of Chattrogram city in Bangladesh, and life time cancer risk from multi-pathway intakes of the trihalomethanes (THMs) to the city dwellers. A total of 11 water samples were collected from the distribution network of the city, and few water quality parameters were analyzed in the study. Three empirical models developed by Amy et al. (1998), Rathbun (1996), and Malcolm Pirnie (1993) were used to estimate the level of THMs from measured water quality data, and were denoted as MODEL1, MODEL2 and MODEL3, respectively in the study. Lifetime cancer risk was estimated using predicted chronic daily intakes (CDI) of THMs' species for different exposure routes (ingestion, inhalation and dermal). The total concentrations of THMs ranged between 20 and 440 μg/L, 95–215 μg/L and 162–249 μg/L were predicted by MODEL1, MODEL2 and MODEL3, respectively. An average lifetime cancer risk was predicted as 1.4 × 10−4, 1.1 × 10−4 and 2.9 × 10−4 for oral, inhalation and dermal exposure, respectively from the water supply of the city. Percent contribution to total lifetime cancer risk were predicted as 50, 40 and10 for oral ingestion, inhalation and dermal absorption, respectively. The study revealed that lifetime cancer risk values were higher than minimum risk level set by United States Environmental Protection Agency. The findings of possible occurrence of THMs in the water supply and associated cancer risk might be beneficial as baseline data for further investigation, and help the decision makers regarding the formulation of standards and legislations of THMs.

Exploring applicability of artificial intelligence and multivariate linear regression model for prediction of trihalomethanes in drinking water

Exploring applicability of artificial intelligence and multivariate linear regression model for prediction of trihalomethanes in drinking water

A multivariate Bayesian network analysis of water quality factors influencing trihalomethanes formation in drinking water distribution systems

Controlling disinfection by-products formation while ensuring effective drinking water disinfection is important for protecting public health. However, understanding and predicting disinfection by-product formation under a variety of conditions in drinking water distribution systems remains challenging as disinfection by-product formation is a multifactorial phenomenon. This study aimed to assess the application of Bayesian Network models to predict the concentration of trihalomethanes, the dominant halogenated disinfection by-product class, using various water quality parameters. Naïve Bayesian and semi-naïve Bayesian models were constructed from Sydney and South East Queensland datasets across 15 drinking water distribution systems in Australia. The targeted variable, total trihalomethanes concentration, was discretised into 3 bins (<0.1 mg L−1, 0.1 – 0.2 mg L−1 and >0.2 mg L−1). The Bayesian network structures were built using water quality parameters including concentrations of individual and total trihalomethanes, disinfectant species (free chlorine, monochloramine, dichloramine, total chlorine), nitrogen species (free ammonia, total ammonia, nitrate, nitrite), and other physical/chemical parameters (temperature, pH, dissolved organic carbon, total dissolved solids, conductivity and turbidity). Seven performance parameters, including predictive accuracy and the rates of true and false positive and negative results, were used to assess the accuracy and precision of the Bayesian network models. After evaluating the model performance, the optimum models were selected to be Bayesian network augmented naïve models. These were observed to have the highest predictive accuracies for Sydney (78%) and South East Queensland (94%). Although disinfectant residuals are among the key variables that lead to trihalomethanes formation, potential concentrations of trihalomethanes in distribution systems can be more confidently predicted, in terms of probability associated with a wider range of water quality variables, using Bayesian networks. The modelling procedure developed in this work can now be applied to develop system-specific Bayesian network models for trihalomethanes prediction in other drinking water distribution systems.

Radial basis function artificial neural network (RBF ANN) as well as the hybrid method of RBF ANN and grey relational analysis able to well predict trihalomethanes levels in tap water

Many models have been developed in previous studies for predicting the formation of disinfection by-products (DBPs) in drinking water. However, most of them were linear or log-linear regression models, and generated based on simulated disinfection of source water or treated water in a laboratory other than real tap water, which shows low application potential in practice. In this study, a radial basis function artificial neural network (RBF ANN) as well as the hybrid method of RBF ANN and grey relational analysis (GRA) was proposed to predict trihalomethanes (THMs) levels in real distribution systems. A total of 64 sets of data including THMs levels (trichloromethane (TCM), bromodichloromethane (BDCM) and total-THMs (T-THMs)) and 8 water quality parameters (temperature, pH, UV absorbance at 254 (UVA254), dissolved organic carbon, bromide, residual free chlorine, nitrite and ammonia) were used to train and verify the proposed model. As compared to linear and log-linear regression models (rp = 0.254–0.659; N25 = 46–78%), RBF ANNs for THMs (TCM, BDCM and T-THMs) prediction consistently show higher regression coefficients (rp = 0.760–0.925) and prediction accuracy (N25 = 92–98%), which indicates the high capability of RBF ANN to learn the complex non-linear relationships involved THMs formation. Further analysis shows that RBF ANNs using fewer water quality parameters based on GRA still make excellent performance in THMs prediction (rp = 0.760–0.946; N25 = 92–98%). This result demonstrates that GRA can be an effective technique to facilitate the generation of sound RBF ANN models with fewer factors.

Model of Prediction of Trihalomethanes (THMs) formation in chlorinated water in water treatment plant using Artificial Neural Network

This study focuses on validity of modeling of trihalomethane formation using artificial neural network with a feed-forward back-propagation neural network approach and graphical user interface function of MATLAB at a water treatment plant. Regularly measured parameters, which are conducted by Uyak et al., 2005, consisting of pH, total organic carbon, temperature and applied chlorine dose were utilized to implement the model for forecasting of trihalomethane formation. Attempting to investigate and compare with the use of traditional multiple linear regressions. The default Levenberg-Marquardt algorithm was used for training the network structures. It is noted that the best validation performance depending on the mean square error was 62.8539 at epoch 49. The simulated result tracked the measured data through a regression plot with a correlation coefficient of 0.95842, 0.94717 and 0.93369 for training, validation and test respectively. With respect to simulated testing the model demonstrates great performance in predicting the trihalomethane formation in chlorinated water. It is concluded that the artificial neural network generally is better than the multiple linear regression for forecasting trihalomethane formation.

Effect of THMs concentrations on the redesigning of Bani Suef water distribution system

AbstractControlling trihalomethanes (THMs) formed in water distribution systems (WDS) is an important issue for producing safe drinking water in the last decades. The main objective of this study is to design WDS to minimize THMs formation. Implemented case of Bani Suef water distribution system (BSWDS), Egypt, was modeled and studied for operating scenarios 2020 and 2040 (case study) using WaterCAD software, alternative [1]. Drinking water samples were collected from fifteen points located on BSWDS according to monthly sampling program performed between February and September 2015. Laboratory analysis showed that the total growth rate coefficient was 1.157 day−1, used in THMs prediction by WaterCAD. Three design alternatives [2, 3, 4] were prepared to reduce the formed THMs based on WaterCAD results. Alternative [2] represented new design of alternative [1] through using decreased pipes diameters to study the effect of reducing travel time on minimizing THMs. Alternative [3] was prepared by redesigning alternative [1] using extending new pipelines from dead ends. Alternative [4] was prepared by redesigning alternative [1] through replacing asbestos cement pipes with new UPVC ones. Predicted THMs from alternatives [2, 3, 4] are lower about 27.85, 21.82 and 11.4% than alternative [1], respectively, for 2020. While, for 2040, are lower about 26.41, 20.2 and 11.4%, respectively.

Assessing measurement uncertainty on trihalomethanes prediction through kinetic models in water supply systems

Disinfection of drinking water through chlorine is commonly used in many countries for reducing pathogenic infection problems, but it may pose a risk to human health due to the formation of some by-products, such as trihalomethanes (THMs). For an adequate management of the disinfection process, it is useful to have models capable of simulating THMs concentrations in water supply systems. However, a crucial aspect is the reliability of their performances when used on real systems and the knowledge of the uncertainty of their predictions. The objective of the present paper is to investigate the simulation of THMs formation through calibrated kinetic models, along with the assessment of the measurement uncertainty on the parameters' estimate and on the model predictions. In particular, a first-order, a second-order and a two-phase kinetic model are considered, while the effect of measurement uncertainty is mainly investigated through the first-order second moment (FOSM) method. The analysis performed on a real case study shows that the three considered models have similar performances in terms of predicted concentrations, which suggests using the simplest first-order one. Moreover, the FOSM results reveal that the first-order model is less affected by measurement uncertainty.

Effect of Data Uncertainty on Trihalomethanes Prediction in Water Supply Systems Using Kinetic Models

The present work compares the performances of first and second order kinetic models for predicting trihalomethanes (THMs) formation in a real case-study. The kinetic parameters are evaluated through an automatic calibration procedure, in which a least-squared objective function relating measured and computed residual chlorine and THMs concentrations is adopted. The effect of measurements uncertainty on the calibrated parameters and on THMs concentrations predictions are quantified in terms of confidence limits using the First Order Second Moment approach. The study reveals that the performances of the two models are quite similar, but the second order one results less influenced by uncertainty.

Modeling of THMs and HAAs Formation in Distribution System upon Chlorination

Seasonal variations of trihalomethanes (THMs) and haloacetic acids (HAAs) were investigated within distribution systems of the Yangtze river treatment plant in Nanjing City (China).The investigation was based on one year sampling program, undertaken from the fall and winter of the year 2007 to the spring and summer of the year 2008. A multiple linear regression model was developed to predict THMs and HAAs concentrations in distribution water. Routinely measured parameters including free residual chlorine, ultraviolet light absorbance at 254 nm (UV254), temperature, pH and NH3-N in distribution water was used to develop the model for the prediction of THMs and HAAs. The developed models provided satisfactory estimations of the concentrations of THMs and HAAs and the model regression coefficients of THMs and HAAs are 0.90 and 0.87, respectively. Further, the Durbin-Watson values confirm the reliability of the two models. The results indicate that variations of free residual chlorine, ultraviolet light absorbance at 254 nm (UV254), temperature, pH and NH3-N can described the formation of THMs and HAAs in distribution water by the multiple linear regression technique.