ekipЭкология и промышленность РоссииEcology and Industry of Russia1816-03952413-6042ООО "Калвис"10.18412/1816-0395-2025-2-56-59ekip-2849Research ArticleАНАЛИЗ. МЕТОДИКИ. ПРОГНОЗЫANALYSIS. METHODS. PROGNOSISИспользование искусственного интеллекта в качестве предиктивной модели распространения загрязняющих веществ в атмосферном воздухеUsing Artificial Intelligence as a Predictive Model of Atmospheric Air Pollutant DistributionГусевД.М.GusevD.M.

канд. хим. наук, начальник лаборатории

Cand. Sci. (Chem.), Head of Laboratory

podpiska@kalvis.ruМельниковП.А.MelnikovP.A.

канд. техн. наук, директор института химии и энергетики

Cand. Sci. (Eng.), Director, Institute of Chemistry and Energy

podpiska@kalvis.ruШашенкоВ.А.ShashenkoV.A.

техник лаборатории

Laboratory Technician

podpiska@kalvis.ruТольяттинский государственный университетРоссияTogliatti State UniversityRussian Federation2025180220252925659Copyright © ООО "Калвис", 20252025ООО "Калвис"ООО "Калвис"https://www.ecology-kalvis.ru/jour/about/submissions#copyrightNoticehttps://www.ecology-kalvis.ru/jour/article/view/2849

Представлен опыт применения искусственного интеллекта (ИИ) для создания предиктивной модели распространения загрязняющих веществ в атмосферном воздухе на урбанизированной территории. Рассмотрены различные алгоритмы машинного обучения, их преимущества и недостатки в контексте прогнозирования качества воздуха. Исследованы возможности использования исторических данных, накопленных с 2021 г. по июнь 2024 г. о загрязнении атмосферного воздуха г.о. Тольятти, метеорологических условий, топографии и других факторов, влияющих на распространение загрязняющих веществ, для обучения моделей ИИ. Приведены результаты моделирования, демонстрирующие эффективность разработанной модели в прогнозировании уровней загрязнения в различных временных масштабах. Сделан вывод о значимости применения ИИ в области мониторинга качества воздуха и предложены практические рекомендации по использованию полученных результатов с целью оптимизации стратегий управления загрязнением и обеспечения экологической безопасности.

The experience of using artificial intelligence (AI) to create a predictive model of atmospheric air pollutant distribution in an urbanized area is presented. Various machine learning algorithms, their advantages and disadvantages in the context of air quality prediction are considered. The possibilities of using historical data accumulated from 2021 to June 2024 on atmospheric air pollution in Togliatti, meteorological conditions, topography and other factors affecting the distribution of pollutants for training of AI models are investigated. Simulation results demonstrating the effectiveness of the developed model in predicting pollution levels at different time scales are presented. A conclusion is made about the significance of using AI in the field of air quality monitoring, and practical recommendations for using the obtained results to optimize pollution management strategies and ensure environmental safety are proposed.

искусственный интеллектпредиктивная модельзагрязняющие веществакачество атмосферного воздухаartificial intelligencepredictive modelpollutantsair qualityReferencesRiediker M., Cascio W.E, Griggs T.R. et al. Particulate Matter Exposure in Cars Is Associated with Cardiovascular Effects in Healthy Young Men. Am J Respir Crit Care Med. American Thoracic Society — AJRCCM. 2004. Vol. 169. No. 8. P. 934—940.Riediker M., Cascio W.E, Griggs T.R. et al. Particulate Matter Exposure in Cars Is Associated with Cardiovascular Effects in Healthy Young Men. Am J Respir Crit Care Med. American Thoracic Society — AJRCCM. 2004. Vol. 169. No. 8. P. 934—940.Ghio A.J., Huang Y.-C.T. Exposure to Concentrated Ambient Particles (CAPs). A Review. Inhalation Toxicology. Taylor & Francis, 2004. Vol. 16. No. 1. P. 53—59.Ghio A.J., Huang Y.-C.T. Exposure to Concentrated Ambient Particles (CAPs). A Review. Inhalation Toxicology. Taylor & Francis, 2004. Vol. 16. No. 1. P. 53—59.Uysal N., Schapira R.M. Effects of ozone on lung function and lung diseases. Current Opinion in Pulmonary Medicine. 2003. Vol. 9. No. 2. P. 144.Uysal N., Schapira R.M. Effects of ozone on lung function and lung diseases. Current Opinion in Pulmonary Medicine. 2003. Vol. 9. No. 2. P. 144.Nawrot T.S., Plusquin M., Hogervorst J., Poels H. et al. Environmental exposure to cadmium and risk of cancer: a prospective population-based study. Lancet Oncol. 2006. Vol. 7. No 2. P. 119—126. [Electronic resource]. URL:https://www.thelan cet.com/journals/lanonc/article/PIIS1470-2045(06)70545-9/abstract?isEOP=true (accessed 05.12.2024).Nawrot T.S., Plusquin M., Hogervorst J., Poels H. et al. Environmental exposure to cadmium and risk of cancer: a prospective population-based study. Lancet Oncol. 2006. Vol. 7. No 2. P. 119—126. [Electronic resource]. URL:https://www.thelan cet.com/journals/lanonc/article/PIIS1470-2045(06)70545-9/abstract?isEOP=true (accessed 05.12.2024).Vascular Effects of Ambient Pollutant Particles and Metals: Ingenta Connect [Electronic resource]. URL:https://www.ingentaconnect.com/content/ben/cvp/2006/00000004/00000003/art00004 (accessed 05.06.2024).Vascular Effects of Ambient Pollutant Particles and Metals: Ingenta Connect [Electronic resource]. URL:https://www.ingentaconnect.com/content/ben/cvp/2006/00000004/00000003/art00004 (accessed 05.06.2024).Al-Janabi S., Mohammad M., Al-Sultan A. A new method for prediction of air pollution based on intelligent computation. Soft Computing. Springer. 2020. Vol. 24. No. 1. P. 661—680.Al-Janabi S., Mohammad M., Al-Sultan A. A new method for prediction of air pollution based on intelligent computation. Soft Computing. Springer. 2020. Vol. 24. No. 1. P. 661—680.Liu D. Lee Sh.‐J., Huang Y., Chiu C.‐J. Air pollution forecasting based on attention‐based LSTM neural network and ensemble learning. Expert Systems. 2020. Vol. 37. No. 3. P. e12511.Liu D. Lee Sh.‐J., Huang Y., Chiu C.‐J. Air pollution forecasting based on attention‐based LSTM neural network and ensemble learning. Expert Systems. 2020. Vol. 37. No. 3. P. e12511.Iskandaryan D., Ramos F., Trilles S. Air quality prediction in smart cities using machine learning technologies based on sensor data. A review. Applied Sciences. MDPI, 2020. Vol. 10. No. 7. P. 2401.Iskandaryan D., Ramos F., Trilles S. Air quality prediction in smart cities using machine learning technologies based on sensor data. A review. Applied Sciences. MDPI, 2020. Vol. 10. No. 7. P. 2401.Abdullah S., Ismail M., Ahmed A.N. Multi-layer perceptron model for air quality prediction. Malaysian Journal of Mathematical Sciences. 2019. Vol. 13. P. 85—95.Abdullah S., Ismail M., Ahmed A.N. Multi-layer perceptron model for air quality prediction. Malaysian Journal of Mathematical Sciences. 2019. Vol. 13. P. 85—95.Lim Y.B., Aliyu I., Lim C.G. Air Pollution Matter Prediction Using Recurrent Neural Networks with Sequential Data. Proceedings of the 2019 3rd International Conference on Intelligent Systems, Metaheuristics & Swarm Intelligence. Male Maldives: ACM, 2019. P. 40—44.Lim Y.B., Aliyu I., Lim C.G. Air Pollution Matter Prediction Using Recurrent Neural Networks with Sequential Data. Proceedings of the 2019 3rd International Conference on Intelligent Systems, Metaheuristics & Swarm Intelligence. Male Maldives: ACM, 2019. P. 40—44.Ecological atlas urban district of Togliatti, mobile laboratory. [Electronic resource]. URL:https://emgis.ru/atlas/mel.aspx (accessed 05.06.2024).Ecological atlas urban district of Togliatti, mobile laboratory. [Electronic resource]. URL:https://emgis.ru/atlas/mel.aspx (accessed 05.06.2024).Breiman L. Hinging hyperplanes for regression, classification, and function approximation. IEEE Transactions on Information Theory. IEEE. 1993. Vol. 39. No. 3. P. 999—1013.Breiman L. Hinging hyperplanes for regression, classification, and function approximation. IEEE Transactions on Information Theory. IEEE. 1993. Vol. 39. No. 3. P. 999—1013.Huang X., Xu J., Wang S. Operation optimization for centrifugal chiller plants using continuous piecewise linear programming. 2010 IEEE International Conference on Systems, Man and Cybernetics. IEEE, 2010. P. 1121—1126.Huang X., Xu J., Wang S. Operation optimization for centrifugal chiller plants using continuous piecewise linear programming. 2010 IEEE International Conference on Systems, Man and Cybernetics. IEEE, 2010. P. 1121—1126.

The authors declare that there are no conflicts of interest present.