Application of artificial intelligence technologies for monitoring and optimization of water treatment processes

by

N.A. Zhilnikova

Saint Petersburg State University of Aerospace Instrumentation,

RF, Saint-Petersburg, Bolshaya Morskaia, 67, lit. A

E-mail: n.zhilnikova@guap.ru

DOI: 10.33075/2220-5861-2026-1-105-116

UDC 628.16                                 

EDN: https://elibrary.ru/kpzpkm

This paper explores the prospects of implementing advanced computational methods into the management systems of municipal infrastructure facilities. The primary focus is on utilizing machine learning tools and neural network algorithms to improve the operational performance of wastewater treatment plants. The study systematizes digital technologies applicable at various stages of the technological cycle and proposes a comprehensive methodology for data management, covering the entire pipeline from primary monitoring and sensor signal validation to automated decision-making via digital twins. Technical and organizational barriers hindering the widespread implementation of «smart» systems are examined in detail, including the scarcity of representative datasets, sensor metrological instability, and the complexity of interpreting algorithmic decisions. The economic feasibility of the proposed approach is confirmed by analyzing the real-world experience of enterprises in Russia and Europe, which demonstrates a reduction in energy consumption by 15–26% and chemical reagent usage by 10–20%. Finally, the paper substantiates the necessity of transitioning to hybrid models that combine the flexibility of intelligent data analysis methods with the reliability of fundamental physicochemical equations, thereby ensuring high forecasting accuracy and process stability.

Keywords: artificial intelligence, machine learning, wastewater treatment, digital twin, water treatment optimization, predictive analytics, artificial neural networks

REFERENCES

  1. Zhang S., Jin Y., Chen W., Wang J., Wang Y., and Ren H. Artificial intelligence in wastewater treatment: a data‑driven analysis of status and trends. Chemosphere, 2023, Vol. 336, Art. no. 139163.
  2. Lowe M., Qin R., and Mao X. A review on machine learning, artificial intelligence, and smart technology in water treatment and monitoring. Water, 2022, Vol. 14, No. 9, 1384 p.
  3. Zaghloul M.S. and Achari G. Application of machine learning techniques to model a full‑scale wastewater treatment plant with biological nutrient removal. Journal of Environmental Chemical Engineering, 2022, Vol. 10, No. 3, Art. no. 107430.
  4. Yantzen O.S. Sistema avtomaticheskogo kontrolya i upravleniya ochistki stokov, s tsel’yu ikh vtorichnogo ispol’zovaniya v tekhnologicheskikh rezhimakh proizvodstva (Automatic control and monitoring system of wastewater treatment for its reuse in technological production modes). Tochnaya nauka, 2017, No. 10, pp. 23–26.
  5. Varsegov A.V. Avtomatizatsiya protsessa ochistki stochnykh vod (Automation of the wastewater treatment process). Nauchnyi elektronnyi zhurnal «Meridian», 2020, No. 6 (40), pp. 279–281.
  6. Zhil’nikova N.A. Sozdanie tsifrovoi modeli sistemy vodootvedeniya proizvodstva s ispol’zovaniem iskusstvennykh neironnykh setei (Development of a digital model of an industrial wastewater disposal system using artificial neural networks). Izvestiya Samarskogo nauchnogo tsentra Rossiiskoi akademii nauk, 2025, Vol. 27, No. 3 (125), pp. 67–75.
  7. Zhil’nikova N.A. Model’ integrirovannogo upravleniya vodno‑resursnymi sistemami na osnove tsifrovykh tekhnologii v usloviyakh klimaticheskoi nestabil’nosti (Model of integrated water resources management based on digital technologies under climate instability). Sistemy kontrolya okruzhayushchei sredy, 2025, No 4 (62), pp. 136–146. https://doi.org/10.33075/2220‑5861‑2025‑4‑136‑146.
  8. Kop’eva M.A., Chuikov S.S., and Khalin A.N. Avtomatizatsiya protsessa vodoochistki: sovremennye tekhnologii i perspektivy (Automation of the water treatment process: modern technologies and prospects). Tyumenskii nauchnyi zhurnal, 2025, No. 1 (5), pp. 14–17. https://doi.org/10.24412/3034‑154X‑2025‑1‑14‑17.
  9. Cuxhaven treatment plant reduces aeration energy use by 30% while ensuring effluent water quality compliance. Water Online. Available at: https://www.wateronline.com/doc/cuxhaven-treatment-plant-reduces-aeration-energy-use-by-while-ensuring-effluent-water-quality-compliance-0001(January 13, 2026).
  10. Demo case #3: Intelligent control for wastewater treatment (The Netherlands). OPTAIN Project. Available at: https://www.optain.eu/demo-cases/netherlands-intelligent-control-wastewater-case (January 13, 2026).​
  11. BLUEKOLDING: Hubgrade Performance case study. Veolia Water Technologies. Available at: https://www.veoliawatertechnologies.com/en/case-studies/bluekolding(January 13, 2026).
  12. Furtatova A.S. Mekhanizm povysheniya investitsionnoi privlekatel’nosti proektov razvitiya vodoprovodno‑kanalizatsionnogo khozyaistva Sankt‑Peterburga s uchetom innovatsionno‑resursnogo potentsiala (Mechanism for increasing the investment attractiveness of water supply and sanitation projects in Saint Petersburg considering innovation and resource potential). Estestvenno‑gumanitarnye issledovaniya, 2023, No 4 (48), pp. 576–583.
  13. Larionov V.G. and Treiman M.E. Intellektual’noe upravlenie energopotrebleniem na vodoprovodnykh stantsiyakh na primere Filiala «Vodosnabzhenie» GUP «Vodokanal Sankt‑Peterburga» (Intelligent power consumption control at water supply stations: case study of the “Water Supply” branch of Vodokanal of Saint Petersburg). Vestnik Astrakhanskogo gosudarstvennogo tekhnicheskogo universiteta. Seriya: Ekonomika, 2020, No. 4, pp. 7–14. https://doi.org/10.24143/2073‑5537‑2020‑4‑7‑14.
  14. Makhkamova D.A. Tsifrovizatsiya ekologicheskogo monitoringa: vozmozhnosti i vyzovy v usloviyakh Chetvertoi promyshlennoi revolyutsii (Digitalization of environmental monitoring: opportunities and challenges in the Fourth Industrial Revolution). Ekonomika i sotsium, 2025, No. 6–1 (133), pp. 1176–1179.
  15. Dmitrievskii A.N., Eremin N.A., Lozhnikov P.S., and Stolyarov V.E. Analiz riskov pri ispol’zovanii tekhnologii iskusstvennogo intellekta v neftegazodobyvayushchem komplekse (Risk analysis of using artificial intelligence technologies in the oil and gas production sector). Avtomatizatsiya, telemekhanizatsiya i svyaz’ v neftyanoi promyshlennosti, 2021, No. 7 (576), pp. 17–27. https://doi.org/10.33285/0132‑2222‑2021‑7(576)‑17‑27.
  16. https://vodanews.info/opyt-gup-vodokanal-sankt-peterburga-optimizaciya-vodopodgotovki- s-primeneniem-metodov-matematicheskogo-modelirovaniya (January 13, 2026).
  17. https://mosvodokanal.ru/press/smi/11604/ (January 13, 2026).
  18. https://www.vodokanal-nn.ru/press-tsentr/novosti/rekonstruktsiya-sooruzheniy-pervoy-ocheredi-nizhegorodskoy-stantsii-aeratsii-zavershena/ (January 13, 2026).
  19. https://nashgorod.ru/news/2025-01-15/snizhenie-avariynosti-i-poter-podvedeny-itogi-rosvodokanal-tyumen-2024-goda-5298664 (January 13, 2026).

Loading