Optimizing Water Quality Prediction by Comparing Machine Learning Models in Different States of Alkaline, Acidic, and Neutral

Gege  Mei; Xinyue  Zhang; Ximei  Zhao

doi:10.6180/jase.202606_29(6).0003

Optimizing Water Quality Prediction by Comparing Machine Learning Models in Different States of Alkaline, Acidic, and Neutral

Gege Mei¹, Xinyue Zhang²This email address is being protected from spambots. You need JavaScript enabled to view it., and Ximei Zhao³

¹College of Environment, China University of Geosciences, Wuhan 430000, Hubei, China

²Power China Hua Dong Engineering Corporation Limited, Hangzhou 310000, China

³Shandong Key Laboratory of Eco-Environmental Science for the Yellow River Delta, Shandong University of Aeronautics, Binzhou 256600, Shandong, China

Received: May 18, 2025
Accepted: August 10, 2025
Publication Date: October 19, 2025

Copyright The Author(s). This is an open access article distributed under the terms of the Creative Commons Attribution License (CC BY 4.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are cited.

Download Citation: ||https://doi.org/10.6180/jase.202606_29(6).0003

Anticipating Water Quality (WQ) is vital for overseeing environmental protection and ensuring the well-being of the population, especially when pH levels fluctuate. The goal of this research is to optimize the prediction accuracy of WQ by evaluating and comparing the performance of three Machine Learning (ML) models: Adaptive Boosting (ADAC), Naive Bayes Classifier (NBC), and the Black Winged Kite Algorithm (BWKA) across different states of water pH, including alkaline, acidic, and neutral environments. Hybrid versions were developed to enhance model performance by integrating each base model with pre-existing optimization algorithms. These combinations were evaluated using a comprehensive dataset encompassing physical and chemical WQ indicators. To guarantee dependability and adaptability, each model underwent training and assessment using organized subsets. Evaluation was conducted utilizing performance indicators like accuracy, precision, recall, and F1-score. Among the models, the hybrid ADAC_BWK model demonstrated superior predictive performance with a training accuracy of 0.902 and a testing accuracy of 0.783, outperforming other configurations under all pHscenarios. This result underscores the significance of employing hybrid optimization techniques for improving predictive analytics in environmental applications. The findings contribute to the development of reliable water monitoring systems and can support decision-makers in enhancing drinking water safety and resource planning.

Keywords: Adaptive Boosting Prediction, Naive Bayes, Black Winged Kite Algorithm, Prediction, Machine Learning, Water Quality.

[1] R. Xu, S. Hu, H. Wan, Y. Xie, Y. Cai, and J. Wen, (2024) “A unified deep learning framework for water quality pre diction based on time-frequency feature extraction and data feature enhancement" Journal of Environmental Management 351: 119894. DOI: 10.1016/j.jenvman.2023.119894.
[2] A. F. del Castillo, M. V. Garibay, D. Díaz-Vázquez, C. Yebra-Montes, L. E. Brown, A. Johnson, A. Garcia Gonzalez, and M. S. Gradilla-Hernández, (2024) “Im proving river water quality prediction with hybrid ma chine learning and temporal analysis" Ecological Informatics 82: 102655. DOI: 10.1016/j.ecoinf.2024.102655.
[3] N. Satish, J. Anmala, K. Rajitha, and M. R. R. Varma, (2024) “A stacking ANN ensemble model of ML models for stream water quality prediction of Godavari River Basin, India" Ecological Informatics 80: 102500. DOI: 10.1016/j.ecoinf.2024.102500.
[4] S. Chen, J. Huang, P. Wang, X. Tang, and Z. Zhang, (2024) “A coupled model to improve river water quality prediction towards addressing non-stationarity and data limitation" Water Research 248: 120895. DOI: 10.1016/j.watres.2023.120895.
[5] M. K. Nallakaruppan, E. Gangadevi, M. L. Shri, B. Balusamy, S. Bhattacharya, and S. Selvarajan, (2024) “Reliable water quality prediction and parametricanaly sis using explainable AI models" Scientific Reports 14: 7520. DOI: 10.1038/s41598-024-56775-y.
[6] Q. Tian, W. Luo, and L. Guo, (2024) “Water quality prediction in the Yellow River source area based on the DeepTCN-GRUmodel "Journal of Water Process Engineering 59: 105052. DOI: 10.1016/j.jwpe.2024.105052.
[7] Z. Li, H. Liu, C. Zhang, and G. Fu, (2024) “Real-time water quality prediction in water distribution networks using graph neural networks with sparse monitoring data" Water Research 250: 121018. DOI: 10.1016/j.watres. 2023.121018.
[8] M. Y. Shams, A. M. Elshewey, E.-S. M. El-Kenawy, A. Ibrahim, F. M. Talaat, and Z. Tarek, (2024) “Water quality prediction using machine learning models based on grid search method" Multimedia Tools and Applications 83: 35307–35334. DOI: 10.1007/s11042-023-16737-4.
[9] M. Y. Shams, A. M. Elshewey, E.-S. M. El-Kenawy, A. Ibrahim, F. M. Talaat, and Z. Tarek, (2024) “Water quality prediction using machine learning models based on grid search method" Multimedia Tools and Applications 83: 35307–35334. DOI: 10.1007/s11042-023-16737-4.
[10] J. Sun, X. Guan, X. Sun, X. Cao, Y. Tan, and J. Liao, (2024) “Water quality prediction and carbon reduction mechanisms in wastewater treatment in Northwest cities using Random Forest Regression model" Scientific Re ports 14: 31525. DOI: 10.1038/s41598-024-83277-8.
[11] H. Jeong, S. Park, B. Choi, C. S. Yu, J. Y. Hong, T.-Y. Jeong, and K. H. Cho, (2024) “Machine learning-based water quality prediction using octennial in-situ Daphnia magna biological early warning system data" Journal of Hazardous Materials 465: 133196. DOI: 10.1016/j.jhazmat.2023.133196.
[12] M. Fooladi, M. R. Nikoo, R. Mirghafari, C. A. Madramootoo, G. Al-Rawas, and R. Nazari, (2024) “Robust clustering-based hybrid technique enabling reliable reservoir water quality prediction with uncertainty quantification and spatial analysis" Journal of Environ mental Management 362: 121259. DOI: 10.1016/j.jenvman.2024.121259.
[13] X. Chen, Y. Chen, T. Shimizu, J. Niu, K. Nakagami, X. Qian, B. Jia, J. Nakajima, J. Han, and J. Li, (2017) “Water resources management in the urban agglomeration of the Lake Biwa region, Japan: An ecosystem services based sustainability assessment" Science of the Total Environment 586: 174–187. DOI: 10.1016/j.scitotenv. 2017.01.197.
[14] A. Parsaie and A. H. Haghiabi, (2017) “Numerical routing of tracer concentrations in rivers with stagnant zones" Water Science and Technology: Water Supply 17: 825–834. DOI: 10.2166/ws.2016.175.
[15] R. J. May, G. C. Dandy, H. R. Maier, and J. B. Nixon, (2008) “Application of partial mutual information variable selection to ANN forecasting of water quality in water distribution systems" Environmental Modelling & Software 23: 1289–1299. DOI: 10.1016/j.envsoft.2008.03.008.
[16] S. Palani, S.-Y. Liong, and P. Tkalich, (2008) “An ANN application for water quality forecasting" Marine pollution bulletin 56: 1586–1597. DOI: 10.1016/j.marpolbul.2008.05.021.
[17] A. H.Haghiabi, (2016) “Prediction of longitudinal dispersion coefficient using multivariate adaptive regression splines" Journal of Earth System Science 125: 985 995. DOI: 10.1007/s12040-016-0708-8.
[18] N. S. Jaddi and S. Abdullah, (2017) “A cooperative competitive master-slave global-best harmony search for ANN optimization and water-quality prediction" Ap plied Soft Computing 51: 209–224. DOI: 10.1016/j.asoc.2016.12.011.
[19] S. Emamgholizadeh, H. Kashi, I. Marofpoor, and E. Zalaghi, (2014) “Prediction of water quality parameters of Karoon River (Iran) by artificial intelligence-based models" International Journal of Environmental Science and Technology 11: 645–656. DOI: 10.1007/s13762 013-0378-x.
[20] M.Shokoohi,M.Tabesh, S. Nazif, and M. Dini, (2017) “Water quality based multi-objective optimal design of water distribution systems" Water Resources Manage ment 31: 93–108. DOI: 10.1007/s11269-016-1512-6.
[21] M.R.NikooandN.Mahjouri, (2013) “Water quality zoning using probabilistic support vector machines and self-organizing maps" Water resources management 27: 2577–2594. DOI: 10.1007/s11269-013-0304-5.
[22] S. Heddam, (2016) “Secchi disk depth estimation from water quality parameters: artificial neural network versus multiple linear regression models?" Environmental processes 3: 525–536. DOI: 10.1007/s40710-016-0144-4.
[23] D.-C. Feng, Z.-T. Liu, X.-D. Wang, Y. Chen, J.-Q. Chang, D.-F. Wei, and Z.-M. Jiang, (2020) “Machine learning-based compressive strength prediction for con crete: An adaptive boosting approach" Construction and Building Materials 230: 117000. DOI: 10.1016/j.conbuildmat.2019.117000.
[24] K. W.Walker and Z. Jiang, (2019) “Application of adaptive boosting (AdaBoost) in demand-driven acquisition (DDA) prediction: A machine-learning approach" The Journal of Academic Librarianship 45: 203–212. DOI: 10.1016/j.acalib.2019.02.013.
[25] K. M. Leung, (2007) “Naive bayesian classifier" Poly technic University Department of Computer Science/Finance and Risk Engineering 2007: 123–156.
[26] E. Frank, M. Hall, and B. Pfahringer, (2012) “Locally weighted naive bayes" arXiv preprint arXiv:1212.2487: DOI: 10.48550/arXiv.1212.2487.
[27] F. Zheng and G. I. Webb, (2005) “A comparative study of semi-naive Bayes methods in classification learning" AUSDM05:141–155.
[28] A.Flack,E.O.Aikens,A.Kölzsch,E.Nourani,K.R.S. Snell, W. Fiedler, N. Linek, H.-G. Bauer, K. Thorup, and J. Partecke, (2022) “New frontiers in bird migration research" Current Biology 32: R1187–R1199. DOI: 10.1016/j.cub.2022.08.028.
[29] A. C. Lees and J. J. Gilroy, (2021) “Bird migration: When vagrants become pioneers" Current Biology 31: R1568–R1570. DOI: 10.1016/j.cub.2021.10.058.
[30] Y. Cheng, Z. Wen, X. He, Z. Dong, M. Zhangshang, D. Li, Y. Wang, Y. Jiang, and Y. Wu, (2022) “Ecological traits affect the seasonal migration patterns of breeding birds along a subtropical altitudinal gradient" Avian Re search 13: 100066. DOI: 10.1016/j.avrs.2022.100066.
[31] M.-r. Jiang, X.-f. Feng, C.-p. Wang, X.-l. Fan, and H. Zhang, (2023) “Robust color image watermarking algorithm based on synchronization correction with multi layer perceptron and Cauchy distribution model" Ap plied Soft Computing 140: 110271. DOI: 10.1016/j. asoc.2023.110271.
[32] S. Kadry andV. Rajinikanth, (2021) “Image multi-level thresholding with Mayfly optimization" International Journal of Electrical & Computer Engineering(2088 8708) 11: DOI: 10.11591/ijece.v11i6.pp5420-5429.
[33] K. Zervoudakis and S. Tsafarakis, (2020) “A mayfly optimization algorithm" Computers & Industrial Engineering 145: 106559. DOI: 10.1016/j.cie.2020.106559.
[34] T. Bhattacharyya, B. Chatterjee, P. K. Singh, J. H. Yoon, Z. W. Geem, and R. Sarkar, (2020) “Mayfly in harmony: A new hybrid meta-heuristic feature selection algorithm" IEEE Access 8: 195929–195945. DOI: 10.1109/ACCESS.2020.3031718.
[35] N. S. M. Raja, V. Rajinikanth, and K. Latha, (2014) “Otsu based optimal multilevel image thresholding using firefly algorithm" Modelling and Simulation in Engineering 2014: 794574. DOI: 10.1155/2014/794574.
[36] V. Rajinikanth and M. S. Couceiro. “Optimal multi level image threshold selection using a novel objective function”. In: Information Systems Design and Intelligent Applications: Proceedings of Second International Conference INDIA 2015, Volume 2. Springer, 2015, 177 186. DOI: 10.1007/978-81-322-2247-7_19.