FORECASTING AIR POLLUTION FROM EMISSIONS IN URBAN CANYONS USING ML-CFD MODELING

This paper presents a hybrid approach for predicting pollutant dispersion in urban street canyons, taking into account noise barriers. The methodology combines detailed CFD modeling and a surrogate model based on the BiLSTM neural network architecture with an attention mechanism. Configurations with barrier heights of 0.1H, 0.2H, and 0.3H were studied. CFD calculations revealed a nonlinear effect of barrier height on aerodynamics and the formation of pollutant accumulation zones, with the most complex non-stationary behavior observed at a height of 0.2H. The surrogate model successfully predicts concentration evolution for both the barrier-free and 0.1H barrier cases, demonstrating an average absolute percentage error of less than 15%. For a 0.2H barrier, accuracy decreases in zones of intense turbulence due to the highly non-stationary nature of the process. This approach significantly reduces computational costs while maintaining physical accuracy, which is promising for decision support systems in urban ecology. The model provides accelerated forecasting compared to CFD calculations by 7–8 orders of magnitude, so the inference time showed 1–5 ms, while one CFD simulation takes about 54 hours on the 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