2021
DOI: 10.1016/j.buildenv.2020.107479
|View full text |Cite
|
Sign up to set email alerts
|

Assessing neighborhood variations in ozone and PM2.5 concentrations using decision tree method

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

2
11
0

Year Published

2022
2022
2024
2024

Publication Types

Select...
8

Relationship

0
8

Authors

Journals

citations
Cited by 27 publications
(13 citation statements)
references
References 35 publications
2
11
0
Order By: Relevance
“…In terms of urban morphology, it is found that building density, average building height, and road density all have an impact on PM 2.5 concentration which is consistent with previous research but with some differences, for example, Gao Y. [17] proposed that traffic land and PM 2.5 concentration have a strong correlation, and the correlation is more than that of other urban morphology factors. However, in this study, although road density has a high correlation with PM 2.5 concentration, it is lower than building density, average building height, and other influencing factors.…”
Section: Discussion and Urban Design Recommendationssupporting
confidence: 86%
See 1 more Smart Citation
“…In terms of urban morphology, it is found that building density, average building height, and road density all have an impact on PM 2.5 concentration which is consistent with previous research but with some differences, for example, Gao Y. [17] proposed that traffic land and PM 2.5 concentration have a strong correlation, and the correlation is more than that of other urban morphology factors. However, in this study, although road density has a high correlation with PM 2.5 concentration, it is lower than building density, average building height, and other influencing factors.…”
Section: Discussion and Urban Design Recommendationssupporting
confidence: 86%
“…However, in a real urban situation, the prediction environment of air pollutants is very complex, and there may be a strong nonlinear relationship between air pollutants and the predictors, which leads to great limitations of the multiple linear regression model to predict results. Machine learning algorithms obviously show great superiority in solving nonlinear model problems [17] and support vector machine [18], multi-layer perceptron [19], and sequence learning [20] have been applied to air pollution research and proved to perform well, but they cannot rank the influencing variables based on their importance, which cannot provide a basis for further pollution control and prevention.…”
Section: Introductionmentioning
confidence: 99%
“…5 a, PM 2.5 was typically negatively correlated with O 3 in winter, which was consistent with previous findings ( Wang et al., 2014 ). A similar finding of an increased urban ozone concentration was highly correlated with a higher solar radiation and decreased building height was also observed in May 2018 in Shanghai using a land use regression ( Gao et al., 2021 ). However, a decreased building density, plot ratio, and increased porosity can also promote the diffusion of NO x and reduce the titration of NO X to O 3 ( Lian et al., 2020 ; Ma et al., 2019 ).…”
Section: Resultssupporting
confidence: 72%
“…It is, therefore, necessary to investigate the relationship between air pollution and the neighborhood environment. Gao et al (2021) examined how urban form and meteorology affected the neighborhood ozone (O 3 ) and PM 2.5 distribution. The results revealed that meteorological factors primarily influenced O 3 concentration while PM 2.5 concentration was heavily affected by urban form, mainly in residential areas.…”
Section: Literature Reviewsmentioning
confidence: 99%
“…Deep learning-based approaches such as LSTM, multi-layer perceptron, and support vector machines perform well when processing and analyzing non-linear data (Lu and Wang, 2014). Traditional parametric, statistics-based approaches can determine the importance of variables through the coefficients of explanatory variables on dependent variables, while deep learning-based approaches cannot compute the variable importance (Gao et al, 2021). Thus, this study proposed using random forest, a type of decision-tree model, to calculate the importance of variables.…”
Section: Literature Reviewsmentioning
confidence: 99%