We investigate the flow characteristics around step-up street canyons with various building aspect ratios (ratio of along-canyon building length to street-canyon width, and upwind building height to downwind building height) using a computational fluid dynamics (CFD) model. Simulated results are validated against experimental wind-tunnel results, with the CFD simulations conducted under the same building configurations as those in the wind-tunnel experiments. The CFD model reproduces the measured in-canyon vortex, rooftop recirculation zone above the downwind building, and stagnation point position reasonably well. We analyze the flow characteristics, focusing on the structural change of the in-canyon flows and the interaction between the in- and around-canyon flows with the increase of building-length ratio. The in-canyon flows undergo development and mature stages as the building-length ratio increases. In the development stage (i.e., small building-length ratios), the position of the primary vortex wanders, and the incoming flow closely follows both the upstream and downstream building sidewalls. As a result, increasing momentum transfer from the upper layer contributes to a momentum increase in the in-canyon region, and the vorticity in the in-canyon region also increases. In the mature stage (i.e., large building-length ratios), the primary vortex stabilizes in position, and the incoming flow no longer follows the building sidewalls. This causes momentum loss through the street-canyon lateral boundaries. As the building-length ratio increases, momentum transfer from the upper layer slightly decreases, and the reverse flow, updraft, and streamwise flow in the in-canyon region also slightly decrease, resulting in vorticity reduction.

Particulate matter (PM) as an air pollutant is harmful to the human body as well as to the ecosystem. It is crucial to understand the spatiotemporal PM distribution in order to effectively implement reduction methods. However, ground-based air quality monitoring sites are limited in providing reliable concentration values owing to their patchy distribution. Here, we aimed to predict daily PM₁₀ concentrations using boosting algorithms such as gradient boosting machine (GBM), extreme gradient boost (XGB), and light gradient boosting machine (LightGBM). The three models performed well in estimating the spatial contrasts and temporal variability in daily PM₁₀ concentrations. In particular, the LightGBM model outperformed the GBM and XGM models, with an adjusted R² of 0.84, a root mean squared error of 12.108 μg/m², a mean absolute error of 8.543 μg/m², and a mean absolute percentage error of 16%. Despite having high performance, the LightGBM model showed low spatial prediction accuracy near the southwest part of the study area. Additionally, temporal differences were found between the observed and predicted values at high concentrations. These outcomes indicate that such methods can provide intuitive and reliable PM₁₀ concentration values for the management, prevention, and mitigation of air pollution. In the future, performance accuracy could be improved through consideration of different variables related to spatial and seasonal characteristics.