Neural network method of an analysis and forecasting water quality parameters to ensure public health safety

Introduction. Water quality is a critical factor in public health and sustainable environmental development. With increasing anthropogenic pressure and climate change, traditional methods of water quality monitoring are not sufficiently effective, requiring the innovative approaches based on artificial intelligence.

Objective. To develop and test a hybrid neural network model for accurate prediction water quality indicators.

Materials and methods. The study used a set of software tools on the Python platform with the use of machine learning libraries (TensorFlow Keras, Scikit-learn, Pandas). Preliminary data processing was performed using iForest and Lagrange interpolation methods. An original hybrid architecture was developed, combining convolutional neural networks and bidirectional recurrent layers (BiGRU). The model was trained on real water quality monitoring data using fifty epochs and 120 time intervals. The accuracy of the forecasts was evaluated using four metrics (RMSE, MAE, MAPE, R²) and then compared with the traditional ARIMA and SMA methods.

Results. The hybrid neural network model demonstrated unprecedented forecasting accuracy with a coefficient of determination R²>0.995 for key water quality parameters. The mean prediction error (RMSE) was 0.0309, which is 44.5% better than the results of the closest analogue and 32.2 times better than classical methods. The time required to generate a forecast for the next day does not exceed 0.83 seconds. The model works effectively in conditions of stable indicators, identifying key factors affecting water quality.

Limitations. The analysis was conducted on data for the period 2014–2022, which limits the assessment of long-term trends and extreme events. Model performance decreases when there are more than 5% anomalous values ​​and gaps in the original data without pre-processing.

Conclusion. The developed hybrid neural network model is an effective tool for operational forecasting and control of water resources quality. Its application opens up opportunities for creating early warning systems for potential threats to public health, optimizing water treatment processes, and developing preventive measures to protect aquatic ecosystems. The high accuracy and speed of the model ensure its practical applicability in real-world drinking water source monitoring systems.

Compliance with ethical standards. This study does not require the conclusion of a biomedical ethics committee or other documents.

Contribution:
Shiryayeva M.A. — research concept and design, data collection and processing, text writing;
Pushkareva M.V. — data collection and processing, text writing.
All authors are responsible for the integrity of all parts of the manuscript and approval of the manuscript final version.

Conflict of interest. The authors declare no conflict of interest.

Funding. The study had no sponsorship.

Received: November 21, 2025 / Revised: December 9, 2025 / Accepted: December 19, 2025 / Published: February 10, 2026

1. Liao Z., Wang X., Zhang Y., Qing H., Li C., Liu Q., et al. An integrated simulation framework for NDVI pattern variations with dual society-nature drives: A case study in Baiyangdian Wetland, North China. Ecol. Indic. 2024; 158: 111584. https://doi.org/10.1016/j.ecolind.2024.111584

2. Karpenko N.P., Glazunova I.V., Shiryaeva M.A. Analysis of geo ecological problems and assessment of the availability of drinking water in the Klinsky district of the Moscow region. Prirodoobustroistvo. 2023; (5): 88–94. https://elibrary.ru/qxbsla (in Russian)

3. Shivam K., Tzou J.C., Wu S.C. Multi-step short-term wind speed prediction using a residual dilated causal convolutional network with nonlinear attention. Energies. 2020; 13(7): 1772. https://doi.org/10.3390/en13071772

4. Wu G.D., Lo S.L. Predicting real-time coagulant dosage in water treatment by artificial neural networks and adaptive network-based fuzzy inference system. Eng. Appl. Artif. Intell. 2008; 21(8): 1189–95. https://doi.org/10.1016/j.engappai.2008.03.015

5. Ho J.Y., Afan H.A., El-Shafie A.H., Koting S.B., Mohd N.S., Jaafar W.Z.B., et al. Towards a time and cost effective approach to water quality index class prediction. J. Hydrol. 2019; 575: 148–65. https://doi.org/10.1016/j.jhydrol.2019.05.016

6. Juwana I., Muttil N., Perera B.J.C. Uncertainty and sensitivity analysis of West Java Water Sustainability Index – a case study on Citarum catchment in Indonesia. Ecol. Indic. 2016; 61: 170–8. https://doi.org/10.1016/j.ecolind.2015.08.034

7. Rosenthal O.M., Fedotov V.Kh. Identification of water polluting enterprises based on neural network analysis. Prirodoobustroistvo. 2023; (1): 62–8. https://doi.org/10.26897/1997-6011-2023-1-62-68 https://elibrary.ru/zwfbzm (in Russian)

8. Shamsutdinova T.M. Application of neural network modeling in problems of predicting the level of river floods. Vestnik Novosibirskogo gosudarstvennogo universiteta. Seriya: Informatsionnye tekhnologii. 2023; 21(2): 39–50. https://doi.org/10.25205/1818-7900-2023-21-2-39-50 https://elibrary.ru/kzcoem (in Russian)

9. Shitikov V.K., Zinchenko T.D., Golovatiyuk L.V. Methods of neural networks for estimation of superficial waters quality by usage of hydrobiological exponents. Izvestiya Samarskogo nauchnogo tsentra Rossiiskoi akademii nauk. 2002; 4(2): 280–9. https://elibrary.ru/gjjgkj (in Russian)

10. Sarkar A., Pandey P. River water quality modelling using artificial neural network technique. Aquat. Procedia. 2015; 4: 1070–7. https://doi.org/10.1016/j.aqpro.2015.02.135

11. Karpenko N.P., Lomakin I.M., Drozdov V.S. Management issues of geoenvironmental risks in the assessment of groundwater quality in urban areas. Prirodoobustroistvo. 2019; (5): 106–11. https://doi.org/10.34677/1997-6011/2019-5-106-111 https://elibrary.ru/kbulot (in Russian)

12. Litvinova A.A., Dement’yev A.A., Lyapkalo A.A., Korshunova E.P. Comparative characteristics of quality parameters of waters of the Oka River in places of water intake of utility and drinking water system in Ryazan. Rossiiskii mediko-biologicheskii vestnik imeni akademika I.P. Pavlova. 2022; 30(4): 481–8. https://doi.org/10.17816/PAVL0VJ89568 (in Russian)

13. Zholdakova Z.I., Sinitsyna O.O., Turbinsky V.V. About adjustment of requirements to zones of sanitary protection of sources of the centralized economic and drinking water supply of the population. Gigiena i Sanitaria (Hygiene and Sanitation, Russian journal). 2021; 100(11): 1192–7. https://doi.org/10.47470/0016-9900-2021-100-11-1192-1197 https://elibrary.ru/ymbylm (in Russian)

14. Karpenko N.P., Shiryaeva M.A. Three-dimensional modeling as a system for displaying total chemical soil pollution. Prirodoobustroistvo. 2021; (1): 6–13. https://doi.org/10.26897/1997-6011-2021-1-6-14 https://elibrary.ru/xbuuer (in Russian)

15. Lagutina N.V., Novikov A.V., Sumarukova O.V., Naumenko N.O. Assessment of the water quality of the Rybinsk reservoir as a result of the water level lowering. Prirodoobustroistvo. 2019; (2): 122–6. https://doi.org/10.34677/1997-6011/2019-2-122-126 https://elibrary.ru/yjrivg (in Russian)

16. Shiryayeva M.A., Sinitsyna O.O., Pushkareva M.V., Turbinsky V.V. Algorithm for predicting water quality indicators in water bodies using a neural network. Health Risk Analysis. 2024; (4): 50–62. https://doi.org/10.21668/health.risk/2024.4.05.eng

17. Liu H., Zhang F., Tan Y., Huang L., Li Y., Huang G., et al. Multi-scale quaternion CNN and BiGRU with cross self-attention feature fusion for fault diagnosis of bearing. Meas. Sci. Technol. 2024; 35(8): 086138. https://doi.org/10.1088/1361-6501/ad4c8e

18. Jiang Y., Li C., Sun L., Guo D., Zhang Y., Wang W. A deep learning algorithm for multi-source data fusion to predict water quality of urban sewer networks. J. Clean. Prod. 2021; 318: 128533. https://doi.org/10.1016/j.jclepro.2021.128533

19. Veerendra G.T.N., Kumaravel B., Kodanda Rama Rao P., Dey S., Phani Manoj A.V. Forecasting models for surface water quality using predictive analytics. Environ. Dev. Sustain. 2024; 26(6): 15931–51. https://doi.org/10.1007/s10668-023-03280-3

20. Chen X., Jiang Z., Cheng H., Zheng H., Cai D., Feng Y. A novel global average temperature prediction model – based on GM-ARIMA combination model. Earth Sci. Inform. 2023; 17(1): 853–66. https://doi.org/10.1007/s12145-023-01179-1

21. Jiao G., Chen S., Wang F., Wang Z., Wang F., Li H., et al. Water quality evaluation and prediction based on a combined model. Appl. Sci. 2023; 13(3): 1286. https://doi.org/10.3390/app13031286

22. da Silva A.C., das Graças Braga da Silva F., de Mello Valério V.E., Lima Silva A.T.Y., Marques S.M., Tosta dos Reis J.A. Application of data prediction models in a real water supply network: comparison between arima and artificial neural networks. Rev. Bras. Recur. Hídr. 2024; 29: e12. https://doi.org/10.1590/2318-0331.292420230057

23. Deng T., Chau K.W., Duan H.F. Machine learning based marine water quality prediction for coastal hydro-environment management. J. Environ. Manage. 2021; 284: 112051. https://doi.org/10.1016/j.jenvman.2021.112051

24. Lu X., Dong Y., Liu Q., Zhu H., Xu X., Liu J., et al. Simulation on TN and TP distribution of sediment in Liaohe estuary national wetland park using mike21-coupling model. Water. 2023; 15(15): 2727. https://doi.org/10.3390/w15152727

25. Kim J., Seo D., Jang M., Kim J. Augmentation of limited input data using an artificial neural network method to improve the accuracy of water quality modeling in a large lake. J. Hydrol. 2021; 602(4): 126817. https://doi.org/10.1016/j.jhydrol.2021.126817