Metrological support for the control of wastewater composition: application of neural networks in measurement result processing methods

This article examines the metrological support for wastewater monitoring required to reduce water pollution, from assessing the initial quality of effl uents to monitoring the effectiveness of their treatment before discharge into natural waters. A priority innovative task for water-intensive chemical industries is described: comparing the results of measurements of various parameters of water composition and properties to selectively reduce the concentration of particularly hazardous toxicants. The need to improve the methodology for identifying (and subsequently removing) pollutants that most signifi cantly increase environmentally hazardous chemical and biological oxygen demand is demonstrated. A comparison of metrological analysis methods, such as predictive mathematics, traditional regression analysis, and neural networks, is conducted using the example of a study of wastewater from the sewer system of the Kemerovo Nitrogen Industry Enterprise “AZOT”. Neural networks are shown to be the most effective method, as they have been used to establish the most comprehensive and maximum number of cause-and-effect relationships, including nonlinear ones, between pollutants and chemical and biological oxygen demand, compared to other methods. Based on the results of the study, it is recommended to use neural networks to analyze the cause-and-effect relationships of measured values of the composition and properties of wastewater for metrological support of water and environmental safety of industrial wastewater disposal in nitrogen production.

1. Zykov V. N., Chernyshov V. I. Ecological metrology. RUDN, Moscow (2008). (In Russ.)

2. Freidkina E. M., Treiman M. G. Economic assessment of the impact of industrial enterprises on the environment. Higher School of Economics of St. Petersburg State University of Industrial Technologies, St. Petersburg (2016). (In Russ.)

3. Danilov-Danilyan V. I., Rozental O. M. Hypothesis on the causes of strong variability of impurity concentrations in natural waters. Reports of the Russian Academy of Sciences. Earth Sciences, (1), 114–119 (2023). (In Russ.) https://doi.org/10.31857/S2686739722602502 ; https://elibrary.ru/tjawpk

4. Tsygankova L. E., Vigdorovich V. I., Uryadnikov A. A. Estimation of ecotoxicants solutions toxicity. Vestnik TSU, ((2), 797–800 (2014). (In Russ.) https://elibrary.ru/sauinf

5. Serenkov P. S., Savkova E. N., Pavlov K. A. Concept of development of evidence base of modern metrology. Technical component of measurement process. Electrical and information complexes and systems, (2), 97–105 (2014). (In Russ.) https://elibrary.ru/snohah

6. Ordinartseva N. P. Calibration experiments using the hybrid regression analysis method. Izmeritelnaya Tekhnika, (4), 14–16 (2013). (In Russ.) https://elibrary.ru/qinwkz

7. Kuzin A. Yu., Kroshkin A. N., Isaev L. K., Bulygin F. V., Voitko V. D. Practical aspects of using artifi cial intelligence in metrology. Izmeritelnaya Tekhnika, (9), 66–72 (2023). (In Russ.) https://doi.org/10.32446/0368-1025it.2023-9-66-72 ; https://elibrary.ru/qyxvew

8. Rosenthal O. M., Fedotov V. H. Solution of metrological water-ecological problems by methods of fuzzy logic. Izmeritelnaya Tekhnika, 74(2), 55–63 (2025). (In Russ.) https://doi.org/10.32446/0368-1025it.2025-2-55-63 ; https://elibrary.ru/mzjonu

9. Aprelev A. V., Belyaev V. S., Shorin V. N. Metrology of digital information fl ows in packet data networks. Al’manac of modern metrology, (2), 180–191 (2019). (In Russ.) https://elibrary.ru/xlrmhn

10. Antonova E. N. Sequential algorithm for detecting discrepancies in multidimensional time series with high dynamics. Information systems. Automation and control systems. Bulletin of SPbGTI(TU), (63), 93–99 (2022). (In Russ.) https://doi.org/10.36807/1998-9849-2022-63-89-93-99 ; https://elibrary.ru/bhigyx

11. Kuzin A. Yu., Kroshkin A. N., Obolensky I. A. Artifi cial intelligence-based neuro-consultant in the fi eld of legal metrology. Izmeritelnaya Tekhnika, 73(10), 65-72 (2024). (In Russ.) https://doi.org/10.32446/0368-1025it.2024-10-65-72 ; https://elibrary.ru/harrfl

12. Schölkopf B., Janzing D., Peters J., Sgouritsa E., Zhang K., Mooij J. Semi-supervised learning in causal and anticausal settings, in Empirical Inference, eds B. Schölkopf, Z. Luo, and V. Vovk. Springer, Berlin, Heidelberg, 129–141 (2013). https://doi.org/10.1007/978-3-642-41136-6_13

13. Mooij J. M., Peters J., Janzing D., Zscheischler J., Schölkopf B. Distinguishing cause from effect using observational data: methods and benchmarks. Journal of Machine Learning Research, (17), 1103–1204 (2016). http://jmlr.org/papers/volume17/14-518/14-518.pdf

14. Lopez-Paz D., Muandet K., Recht B. The randomized causation coeffi cient. Journal of Machine Learning Research, (16), 2901–2907 (2015). https://doi.org/10.15496/publikation-11750

15. Friston K. J. Functional and effective connectivity: a review. Brain Connect, 11(1), 13–36 (2011). https://doi.org/10.1089/brain.2011.0008

16. Chicharro D. Parametric and non-parametric criteria for causal inference from time-series. In: Wibral, M., Vicente R., Lizier J. (eds). Directed Information Measures in Neuroscience. Understanding Complex Systems. Springer, Berlin, Heidelberg (2014). https://doi.org/10.1007/978-3-642-54474-3_8

17. Podkorytova O. A., Sokolov M. V. Time Series Analysis. Yurait, Moscow (2025).

18. Mkhitaryan V. S. Data Analysis in MS Excel. KURS, Moscow (2025). (In Russ.)

19. Borovikov V. P. Statistica Neural Networks: Methodology and Technology of Modern Data Analysis. StatSoft, Moscow (2015). (In Russ.)

20. Carrera J., Vicent T., Lafuente J. Effect of the COD/N ratio of the infl uent on the biological nitrogen removal (BNR) from industrial wastewater with high ammonium content. Biochemical Process, 39(12), 2035–2041 (2004). https://doi.org/10.1016/j.procbio.2003.10.005

21. Baum Ch. F., Hurn Stan, Otero Jesús. Testing for time-varying Granger causality. Promoting Communications on Statistics and Stata, (2), 355–378 (2022). https://doi.org/10.1177/1536867X221106403.