Comparative Analysis of the Impact of Built Environment and Land Use on Monthly and Annual Mean PM<sub>2.5</sub> Levels

Urban planners are progressively recognizing the significant effects of the built environment and land use on PM<sub>2.5</sub> levels. However, in analyzing the drivers of PM<sub>2.5</sub> levels, researchers’ reliance on annual mean and seasonal means may overlook the monthl...

Full description

Saved in:
Bibliographic Details
Main Authors: Anjian Song, Zhenbao Wang, Shihao Li, Xinyi Chen
Format: Article
Language:English
Published: MDPI AG 2025-06-01
Series:Atmosphere
Subjects:
Online Access:https://www.mdpi.com/2073-4433/16/6/682
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849467521033306112
author Anjian Song
Zhenbao Wang
Shihao Li
Xinyi Chen
author_facet Anjian Song
Zhenbao Wang
Shihao Li
Xinyi Chen
author_sort Anjian Song
collection DOAJ
description Urban planners are progressively recognizing the significant effects of the built environment and land use on PM<sub>2.5</sub> levels. However, in analyzing the drivers of PM<sub>2.5</sub> levels, researchers’ reliance on annual mean and seasonal means may overlook the monthly variations in PM<sub>2.5</sub> levels, potentially impeding accurate predictions during periods of high pollution. This study focuses on the area within the Sixth Ring Road of Beijing, China. It utilizes gridded monthly and annual mean PM<sub>2.5</sub> data from 2019 as the dependent variable. The research selects 33 independent variables from the perspectives of the built environment and land use. The Extreme Gradient Boosting (XGBoost) method is employed to reveal the driving impacts of the built environment and land use on PM<sub>2.5</sub> levels. To enhance the model accuracy and address the randomness in the division of training and testing sets, we conducted twenty comparisons for each month. We employed Shapley Additive Explanations (SHAP) and Partial Dependence Plots (PDP) to interpret the models’ results and analyze the interactions between the explanatory variables. The results indicate that models incorporating both the built environment and land use outperformed those that considered only a single aspect. Notably, in the test set for April, the R<sup>2</sup> value reached up to 0.78. Specifically, the fitting accuracy for high pollution months in February, April, and November is higher than the annual mean, while July shows the opposite trend. The coefficient of variation for the importance rankings of the seven key explanatory variables exceeds 30% for both monthly and annual means. Among these variables, building density exhibited the highest coefficient of variation, at 123%. Building density and parking lots density demonstrate strong explanatory power for most months and exhibit significant interactions with other variables. Land use factors such as wetlands fraction, croplands fraction, park and greenspace fraction, and forests fraction have significant driving effects during the summer and autumn seasons months. The research on time scales aims to more effectively reduce PM<sub>2.5</sub> levels, which is essential for developing refined urban planning strategies that foster healthier urban environments.
format Article
id doaj-art-d44dc4f9d4d94a978d302dc2f121b80e
institution Kabale University
issn 2073-4433
language English
publishDate 2025-06-01
publisher MDPI AG
record_format Article
series Atmosphere
spelling doaj-art-d44dc4f9d4d94a978d302dc2f121b80e2025-08-20T03:26:10ZengMDPI AGAtmosphere2073-44332025-06-0116668210.3390/atmos16060682Comparative Analysis of the Impact of Built Environment and Land Use on Monthly and Annual Mean PM<sub>2.5</sub> LevelsAnjian Song0Zhenbao Wang1Shihao Li2Xinyi Chen3School of Architecture and Art, Hebei University of Engineering, Handan 056038, ChinaSchool of Architecture and Art, Hebei University of Engineering, Handan 056038, ChinaSchool of Architecture and Urban Planning, Beijing University of Civil Engineering and Architecture, Beijing 100032, ChinaSchool of Architecture, Tianjin University, Tianjin 300072, ChinaUrban planners are progressively recognizing the significant effects of the built environment and land use on PM<sub>2.5</sub> levels. However, in analyzing the drivers of PM<sub>2.5</sub> levels, researchers’ reliance on annual mean and seasonal means may overlook the monthly variations in PM<sub>2.5</sub> levels, potentially impeding accurate predictions during periods of high pollution. This study focuses on the area within the Sixth Ring Road of Beijing, China. It utilizes gridded monthly and annual mean PM<sub>2.5</sub> data from 2019 as the dependent variable. The research selects 33 independent variables from the perspectives of the built environment and land use. The Extreme Gradient Boosting (XGBoost) method is employed to reveal the driving impacts of the built environment and land use on PM<sub>2.5</sub> levels. To enhance the model accuracy and address the randomness in the division of training and testing sets, we conducted twenty comparisons for each month. We employed Shapley Additive Explanations (SHAP) and Partial Dependence Plots (PDP) to interpret the models’ results and analyze the interactions between the explanatory variables. The results indicate that models incorporating both the built environment and land use outperformed those that considered only a single aspect. Notably, in the test set for April, the R<sup>2</sup> value reached up to 0.78. Specifically, the fitting accuracy for high pollution months in February, April, and November is higher than the annual mean, while July shows the opposite trend. The coefficient of variation for the importance rankings of the seven key explanatory variables exceeds 30% for both monthly and annual means. Among these variables, building density exhibited the highest coefficient of variation, at 123%. Building density and parking lots density demonstrate strong explanatory power for most months and exhibit significant interactions with other variables. Land use factors such as wetlands fraction, croplands fraction, park and greenspace fraction, and forests fraction have significant driving effects during the summer and autumn seasons months. The research on time scales aims to more effectively reduce PM<sub>2.5</sub> levels, which is essential for developing refined urban planning strategies that foster healthier urban environments.https://www.mdpi.com/2073-4433/16/6/682built environmentland usePM<sub>2.5</sub>Extreme Gradient Boosting (XGBoost)interaction effects
spellingShingle Anjian Song
Zhenbao Wang
Shihao Li
Xinyi Chen
Comparative Analysis of the Impact of Built Environment and Land Use on Monthly and Annual Mean PM<sub>2.5</sub> Levels
Atmosphere
built environment
land use
PM<sub>2.5</sub>
Extreme Gradient Boosting (XGBoost)
interaction effects
title Comparative Analysis of the Impact of Built Environment and Land Use on Monthly and Annual Mean PM<sub>2.5</sub> Levels
title_full Comparative Analysis of the Impact of Built Environment and Land Use on Monthly and Annual Mean PM<sub>2.5</sub> Levels
title_fullStr Comparative Analysis of the Impact of Built Environment and Land Use on Monthly and Annual Mean PM<sub>2.5</sub> Levels
title_full_unstemmed Comparative Analysis of the Impact of Built Environment and Land Use on Monthly and Annual Mean PM<sub>2.5</sub> Levels
title_short Comparative Analysis of the Impact of Built Environment and Land Use on Monthly and Annual Mean PM<sub>2.5</sub> Levels
title_sort comparative analysis of the impact of built environment and land use on monthly and annual mean pm sub 2 5 sub levels
topic built environment
land use
PM<sub>2.5</sub>
Extreme Gradient Boosting (XGBoost)
interaction effects
url https://www.mdpi.com/2073-4433/16/6/682
work_keys_str_mv AT anjiansong comparativeanalysisoftheimpactofbuiltenvironmentandlanduseonmonthlyandannualmeanpmsub25sublevels
AT zhenbaowang comparativeanalysisoftheimpactofbuiltenvironmentandlanduseonmonthlyandannualmeanpmsub25sublevels
AT shihaoli comparativeanalysisoftheimpactofbuiltenvironmentandlanduseonmonthlyandannualmeanpmsub25sublevels
AT xinyichen comparativeanalysisoftheimpactofbuiltenvironmentandlanduseonmonthlyandannualmeanpmsub25sublevels