ПРОГНОЗИРОВАНИЕ ЗАГРЯЗНЕНИЯ ВОЗДУШНОЙ СРЕДЫ ОТ ВЫБРОСОВ В ГОРОДСКИХ КАНЬОНАХ С ИСПОЛЬЗОВАНИЕМ ML-CFD МОДЕЛИРОВАНИЯ

В работе представлен гибридный подход для прогнозирования распространения загрязняющих веществ в городских уличных каньонах с учетом шумозащитных барьеров. Методология объединяет детальное CFD-моделирование и суррогатную модель на основе нейросетевой архитектуры BiLSTM с механизмом внимания. Исследованы конфигурации с барьерами высотой 0.1H, 0.2H и 0.3H. CFD-расчеты выявили нелинейное влияние высоты барьера на аэродинамику и формирование зон накопления примеси, причем наиболее сложный нестационарный режим наблюдается при высоте 0.2H. Суррогатная модель успешно прогнозирует эволюцию концентрации для случаев без барьера и с барьером 0.1H, демонстрируя среднюю абсолютную процентную ошибку менее 15%. Для барьера 0.2H точность снижается в зонах интенсивной турбулентности, что связано с высокой нестационарностью процесса. Подход позволяет значительно сократить вычислительные затраты при сохранении физической достоверности, что перспективно для систем поддержки решений в области городской экологии. Модель обеспечивает ускоренное прогнозирования по сравнению с CFD-расчетом на 7–8 порядков, так потраченное время инференса показало 1–5 мс, тогда как одна CFD-симуляция занимает около 54 часов на CPU.

1. World Health Organization. Ambient (outdoor) air pollution. World Health Organization (2023). URL: https://www.who.int/ru/news-room/fact-sheets/detail/ambient-(outdoor)-air-quality-and-health

2. Turner, M.C., Andersen, Z.J., Baccarelli, A., Diver, W.R., Gapstur, S.M., Pope, C.A., Prada, D., Samet, J., Thurston, G., and Cohen, A. Outdoor air pollution and cancer: An overview of the current evidence and public health recommendations. CA: A Cancer Journal for Clinicians, 70 (6), 460–479 (2020). https://doi.org/10.3322/caac.21632

3. Singh, J., Payra, S., and Verma, S. Air quality and human health. In: Geospatial Analytics for Environmental Pollution Modeling, pp. 317–352 (Cham: Springer, 2023). https://doi.org/10.1007/978-3-03145300-7_13

4. Hänninen, O., Lehtomäki, H., Korhonen, A., Kokkola, T., Hartikainen, A., Sippula, O., HaverinenShaughnessy, U., Leviäkangas, P., and Rumrich, I.K. Health risks related to air pollution by transport categories and vehicle types: Comparison by mortality indicators. Environment International, 202, 109657 (2025). https://doi.org/10.1016/j.envint.2025.109657

5. Lolli, S. Urban PM2.5 concentration monitoring: A review of recent advances in ground-based, satellite, model, and machine learning integration. Urban Climate, 63, 102566 (2025). https://doi.org/10.1016/j.uclim.2025.102566

6. Natterer, E.S., Rao, S.R., Tejada Lapuerta, A., Engelhardt, R., Hörl, S., and Bogenberger, K. Machine learning surrogates for agent-based models in transportation policy analysis. Transportation Research Part C: Emerging Technologies, 180, 105360 (2025). https://doi.org/10.1016/j.trc.2025.105360

7. Xia, F., Cheng, X., Lei, Z., Liu, Y., Wang, J., and Zhang, H. Heterogeneous impacts of local traffic congestion on local air pollution within a city: Utilizing taxi trajectory data. Journal of Environmental Economics and Management, 122, 102896 (2023). https://doi.org/10.1016/j.jeem.2023.102896

8. Santiago, J.L., Sanchez, B., Quaassdorff, C., de la Paz, D., Martilli, A., Martín, F., and Lechón, Y. Performance evaluation of a multiscale modelling system applied to particulate matter dispersion in a real traffic hot spot in Madrid (Spain). Atmospheric Pollution Research, 11 (1), 141–155 (2020). https://doi.org/10.1016/j.apr.2019.10.001

9. Lin, C., Wang, Y., Ooka, R., Flageul, C., Kim, Y., Kikumoto, H., Wang, Z., and Sartelet, K. Modeling of street-scale pollutant dispersion by coupled simulation of chemical reaction, aerosol dynamics, and CFD. Atmospheric Chemistry and Physics, 23, 1421–1436 (2023). https://doi.org/10.5194/acp-23-1421-2023

10. Vahidi, S., Yeganeh, M., and Ghasaban, M. The effect of the morphology of highly polluted urban areas neighborhood on suspended particles of PM2.5 and PM10 air pollutants (Case study: Ahvaz, Iran). Energy Nexus, 20, 100527 (2025). https://doi.org/10.1016/j.nexus.2025.100527

11. Fellini, S., Majumdar, D., Salizzoni, P., and van Reeuwijk, M. Three-dimensional pollutant dispersion in tree-lined urban canyons: Combined wind-tunnel and LES analysis. Atmospheric Environment, 367, 121748 (2026). https://doi.org/10.1016/j.atmosenv.2025.121748

12. Mousavi, D., Ghaemian, M., and Brinkerhoff, J. Multiscale CFD analysis of urban air pollution dome and ventilation enhancement via an urban chimney. Atmospheric Environment, 337, 120783 (2024). https://doi.org/10.1016/j.atmosenv.2024.120783

13. Huertas, J.I., and Prato, D.F. CFD modeling of near-roadway air pollution. Environmental Modeling & Assessment, 25 (1), 129–145 (2020). https://doi.org/10.1007/s10666-019-09666-w

14. Kikumoto, H., and Ooka, R. Large-eddy simulation of pollutant dispersion in a cavity at fine grid resolutions. Building and Environment, 127, 127–137 (2017). https://doi.org/10.1016/j.buildenv.2017.11.005

15. Reiminger, N., Jurado, X., Vazquez, J., Wemmert, C., and Meunier, G. Methodologies to assess mean annual air pollution concentration combining numerical results and wind roses. Sustainable Cities and Society, 59, 102221 (2020). https://doi.org/10.1016/j.scs.2020.102221

16. Martín, F., Janssen, S., Rodrigues, V., Sousa, J., Santiago, J.L., Rivas, E., Stocker, J., Jackson, R., Russo, F., Villani, M.G., Tinarelli, G., Barbero, D., José, R.S., Pérez-Camanyo, J.L., Santos, G.S., Bartzis, J., Sakellaris, I., Horváth, Z., Környei, L., Cuvelier, C. Using dispersion models at microscale to assess long-term air pollution in urban hot spots: A FAIRMODE joint intercomparison exercise for a case study in Antwerp. Science of the Total Environment, 925, 171761 (2024). https://doi.org/10.1016/j.scitotenv.2024.171761

17. Bi, J., Knowland, K.E., Keller, C.A., and Liu, Y. Combining machine learning and numerical simulation for high-resolution PM2.5 concentration forecast. Environmental Science & Technology, 56 (3), 1544–1556 (2022). https://doi.org/10.1021/acs.est.1c05578

18. Jurado, X., Reiminger, N., Benmoussa, M., Vazquez, J., and Wemmert, C. Deep learning methods evaluation to predict air quality based on computational fluid dynamics. Expert Systems with Applications, 203, 117294 (2022). https://doi.org/10.1016/j.eswa.2022.117294

19. Schulte, N., Snyder, M., Isakov, V., Heist, D., and Venkatram, A. Effects of solid barriers on dispersion of roadway emissions. Atmospheric Environment, 97, 286–295 (2014). https://doi.org/10.1016/j.atmosenv.2014.08.026

20. Venkatram, A., Isakov, V., Deshmukh, P., and Baldauf, R. Modeling the impact of solid noise barriers on near-road air quality. Atmospheric Environment, 141, 462–469 (2016). https://doi.org/10.1016/j.atmosenv.2016.07.005

21. Li, B., Qiu, Z., and Zheng, J. Impacts of noise barriers on near-viaduct air quality in a city: A case study in Xi'an. Building and Environment, 196, 107751 (2021). https://doi.org/10.1016/j.buildenv.2021.107751

22. Wu, Y., and Chen, H. Optimizing block morphology for reducing traffic pollutant concentration in adjacent external spaces of street canyons: A machine learning approach. Building and Environment, 242, 110587 (2023). https://doi.org/10.1016/j.buildenv.2023.110587

23. Mora-Mariano, D., and Flores-Tlacuahuac, A. Bayesian LSTM framework for the surrogate modeling of process engineering systems. Computers & Chemical Engineering, 181, 108553 (2023). https://doi.org/10.1016/j.compchemeng.2023.108553