CFD- and BPNN- based investigation and prediction of air pollutant dispersion in urban environment

This study employed a Computational Fluid Dynamics (CFD)-based back propagation neural network (BPNN) to investigate and predict the pollutant dispersion in an ideal urban environment. The training and test datasets were generated using the Reynolds-averaged Navier-Stokes (RANS) model, which involved 60 cases by varying reference inflow speeds, NO & NO2, and ambient O3 concentrations. The results indicated that the ambient flow was gradually decoupled from the reversed flow at each building's leeward zone further downstream, leading to heightened difficulty in pollutant elimination. Upstream buildings located in front of the emission source were rarely affected by pollutants, regardless of changes in Damkohler numbers (Da). While varying DaNO provides a limited influence, confining DaO3 can effectively reduce hazardous pollutants' impact around the emission source vicinity, on the urban streets, and in the further downstream area of the building array. A budget analysis showed that increasing DaO3 primarily enlarged the chemical reactions' effects on NO increase within the urban residential area. Finally, the BPNN model demonstrated a high accuracy in predicting wind speed and NO con-centration within a few seconds. These findings provide valuable insights for designing effective strategies to mitigate hazardous pollutants' impacts in urban environments.

Automated summary

This study employed computational fluid dynamics and neural network models to investigate and predict pollutant dispersion in urban environments, providing valuable insights for designing effective strategies to mitigate the impacts of hazardous pollutants.