PCA-Based Identification of Built Environment Factors Reducing PM2.5 Pollution in Neighborhoods of Five Chinese Megacities

Abstract

Air pollution, especially PM2.5 pollution, still seriously endangers the health of urban residents in China. The built environment is an important factor affecting PM2.5; however, the key factors remain unclear. Based on 37 neighborhoods located in five Chinese megacities, three relative indicators (the range, duration, and rate of change in PM2.5 concentration) at four pollution levels were calculated as dependent variables to exclude the background levels of PM2.5 in different cities. Nineteen built environment factors extracted from green space and gray space and three meteorological factors were used as independent variables. Principal component analysis was adopted to reveal the relationship between built environment factors, meteorological factors, and PM2.5. Accordingly, 24 models were built using 32 training neighborhood samples. The results showed that the adj_R2 of most models was between 0.6 and 0.8, and the highest adj_R2 was 0.813. Four principal factors were the most important factors that significantly affected the growth and reduction of PM2.5, reflecting the differences in green and gray spaces, building height and its differences, relative humidity, openness, and other characteristics of the neighborhood. Furthermore, the relative error was used to test the error of the predicted values of five verification neighborhood samples, finding that these models had a high fitting degree and can better predict the growth and reduction of PM2.5 based on these built environment factors.

Quantification of the Seasonality and Vertical Dispersion Environment of PM2.5 Variation: A Comparative Analysis of Micro-Scale Wind-Based Buffer Methods

“…Urban environments can influence street-level microclimates (Xu & Chen, 2021), with many reporting an Urban Heat Island (UHI) effect occurring when natural land cover is replaced by built-up urban structures, raising city temperatures (Yin et al, 2018;Yuan et al, 2019) and morphology of trees and buildings can also work together to exacerbate pollution through aerodynamic effects (Jeanjean et al, 2017;Jin et al, 2014). Studies are at their best when they incorporate as many relevant variables as possible while maintaining independence between them, using methods such as Principal Component Analysis (PCA) (Chen & Dai, 2022).…”

“…Height variation can be valuable as configurations with high variations can improve airflow by flushing out PM2.5 pollution and improving ventilation (Hang et al, 2012;Ke et al, 2022). Building/tree footprint and density are one of the more critical indicators (Chen & Dai, 2022), with studies finding that lower densities reduce PM2.5, while 21 higher densities elevate levels due to trapping behaviors (Miskell et al, 2015;Hu et al, 2021).…”

“…Before constructing the regression model, several preprocessing steps were carried out. To identify variables that were most influential for local emission sources, meteorological factors, and the vertical dispersion environment, a Principal Component Analysis (PCA) was performed using the prcomp function in R. PCA can effectively handle a large number of variables and transform them into principal factors that are not correlated with one another , ranking them by their respective contributions to the dependent variable (Chen & Dai, 2022). Typically, variables are iteratively removed based on an explanatory threshold representing the percent of total variance explained by each principal component.…”