Hao, X., Hu, X., Liu, T., Wang, C., & Wang, L. (2022). Estimating Urban PM2.5 Concentration: An Analysis on the Nonlinear Effects of Explanatory Variables Based on Gradient Boosted Regression Tree. Urban Climate, 44, Article 101172.
https://doi.org/10.1016/j.uclim.2022.101172

has been cited by the following article:

• TITLE: Assessment of PM2.5 Distribution at Different Heights in Hanoi, Vietnam

  AUTHORS: Duy An Dam, Thi Thanh Huong Chu, Thi Thu Trang Phung, Van Linh Le, Hong Hiep Nguyen, Quang Lam Nguyen, Thi Thanh Binh Do, Van Dam Vu

  KEYWORDS: Lidar, PM2.5, PM10, Air Monitoring

  JOURNAL NAME: Journal of Geoscience and Environment Protection, Vol.12 No.11, November 28, 2024

  ABSTRACT: Monitoring of PM10 and PM2.5 concentrations frequently is essential for assessing air quality and informing pollution control strategies. This study examines the effect of height on PM2.5 distribution in Hanoi using EPA-standard methods at five rooftop locations on high-rise buildings. Results from Phase 1 (pre-pollution period) indicate a nearly 50% reduction in PM2.5 concentration, decreasing from 34.76 μg/m3 at 40 m to 13.95 μg/m3 at 336 m. In contrast, Phase 2 (pollution wave) showed relatively stable PM2.5 concentrations across heights, likely influenced by cold air masses and wind speed. MLR and MNLR analyses reveal the significant impact of meteorological factors and PM10 on PM2.5 levels, with the MNLR model accounting for 80% - 94% of the variance, outperforming the MLR model’s 50% - 80%. Employing UAVs, Lidar, and synchronized meteorological data is proposed as an advanced approach to enhance the accuracy of height-based dust concentration assessments.