Regression model and artificial neural network model to predict halonitromethane formation from amino acids during UV/monochloramine disinfection in bromide-containing real water
Environmental Pollution · 2025
DOI: 10.1016/j.envpol.2025.127117 ↗Kurz gefasst
Fachartikel in der Zeitschrift Environmental Pollution, 2025. Verfasst von Bohui Xu und 4 weiteren Autor:innen. Beteiligte Einrichtung: Yellow River Engineering Consulting Co., Ltd., Zhengzhou, 450003, China; Department of Municipal Engineering, Southeast University, Nanjing, 211189, …. Hauptthemen laut MEDLINE: Neural Networks, Computer, Disinfection, Water Pollutants, Chemical, Amino Acids. Die Arbeit nennt 55 Literaturangaben. Gefördert von: National Science Foundation, Fundamental Research Funds for the Central Universities, National Natural Science Foundation of China.
Abstract (Originalsprache)
Halonitromethanes (HNMs) were high-toxicity nitrogenous disinfection byproducts generated by amino acids (AAs) during UV/monochloramine (UV/NH2Cl) disinfection in bromide-containing water. HNM concentrations fell over time, highlighting disinfection time optimization as an effective control strategy. Using specific ultraviolet absorbance at 254 nm characterizing aromatic carbon composition, a single equation predicted HNM concentrations generated by three AAs (including tyrosine, tryptophan and aspartic acid) in bromide-containing real water and distilled water combined with NH2Cl dose, disinfection time, Br-, HCO3- and pH. Utilizing a second-order polynomial for disinfection time whose coefficients incorporated NH2Cl dose and water quality parameters, regression model successfully described HNM concentrations, with improved accuracy by introducing nitrate. Due to excellent non-linear fitting abilities, back propagation (BP) and radial basis function (RBF) artificial neural network (ANN) models were applied, followed by principal components analysis (PCA) for data preprocessing and genetic algorithm (GA) for model structure optimization. The predictive performance in descending order was RBF ANN, regression model and BP ANN, with GA optimization outperforming PCA optimization. GA-RBF ANN model achieved R2 = 0.90, mean absolute error = 0.39, mean relative error = 20% and root-mean-square error = 0.68, demonstrating better generalization and 12% fewer hidden layer neurons than RBF ANN model. It was further simplified by removing insignificant pH and HCO3-. HNM-associated cytotoxicity/genotoxicity based on the additivity of toxicity, respectively damaging cells/DNA, had a strong positive linear correlation (R2 > 0.9) with its concentrations. It confirmed HNM concentration control as effective toxicity management. Heatmaps of HNM generation in bromide-containing real water showed that both low NH2Cl doses (e.g., 1684.8 mJ⋅cm-2) could reduce HNM generation.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- Yellow River Engineering Consulting Co., Ltd., Zhengzhou, 450003, China; Department of Municipal Engineering, Southeast University, Nanjing, 211189, China.
- Department of Municipal Engineering, Southeast University, Nanjing, 211189, China.
- Key Laboratory of Original Agro-Environmental Pollution Prevention and Control, Ministry of Agriculture and Rural Affairs (MARA)/ Tianjin Key Laboratory of Agro-Environment and Agro-Product Safety, Agro-Environmental Pr…
- Department of Municipal Engineering, Southeast University, Nanjing, 211189, China. Electronic address: lindeng@seu.edu.cn.
Förderung
- National Science Foundation
- Fundamental Research Funds for the Central Universities
- National Natural Science Foundation of China
Zitieren
APA
Xu, B., Chen, X., Zhang, C., Luo, W., & Deng, L. (2025). Regression model and artificial neural network model to predict halonitromethane formation from amino acids during UV/monochloramine disinfection in bromide-containing real water. Environmental Pollution. https://doi.org/10.1016/j.envpol.2025.127117
Vancouver
Xu B, Chen X, Zhang C, Luo W, Deng L. Regression model and artificial neural network model to predict halonitromethane formation from amino acids during UV/monochloramine disinfection in bromide-containing real water. Environmental Pollution. 2025. doi:10.1016/j.envpol.2025.127117
BibTeX
@article{Xu2025,
author = {Xu, Bohui and Chen, Xiaoliang and Zhang, Changbo and Luo, Wei and Deng, Lin},
title = {Regression model and artificial neural network model to predict halonitromethane formation from amino acids during UV/monochloramine disinfection in bromide-containing real water},
journal = {Environmental Pollution},
year = {2025},
doi = {10.1016/j.envpol.2025.127117}
}
EUVIMED