Investigate the effects of urban land use on PM2.5 concentration: An application of deep learning simulation

Zhao, Liyuan; Zhang, Ming; Cheng, Samantha H.; Fang, Yunhao; Wang, Shuxian; Zhou, Cong

doi:10.1016/j.buildenv.2023.110521

Cited by 15 publications

(4 citation statements)

References 70 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Generally, the PM 2.5 concentrations in the northern part of central Wuhan were higher than the southern part. The industrial emissions from the Qingshan District and external sources of air pollutants invading from the northern provinces (Hebei, Shandong, and Henan) contributed to the PM 2.5 pollution in the northern part (Zhao et al, 2023). Meanwhile, the city center acted as a buffer zone to prevent the spread of PM 2.5 pollutants from the north to the south to some degree (Yu, 2023).…”

Section: Discussionmentioning

confidence: 99%

Exploring the relationships between 3D urban landscape patterns and PM_2.5 pollution using the multiscale geographic weighted regression model

Duan,

Cao,

Wang

et al. 2024

Progress in Physical Geography: Earth and Environment

View full text Add to dashboard Cite

Fine particulate matter (PM2.5) is a major source of air pollution and exerts serious impacts on human health. The 3D urban landscape patterns can significantly affect the diffusion and emissions of PM2.5. However, studies on the relationships between 3D urban landscape patterns and PM2.5 pollution across different seasons remain understudied. With the ground-level air pollutants estimated by the remote sensing and fine-scale building information, this study applied the multiscale geographically weighted regression model to explore such relationships. Wuhan, the largest metropolis in Central China, was selected as the study area for the application of our methodology. The results showed that the direction, degree, and scale of the effect of 3D urban landscape patterns on PM2.5 pollution varied across seasons. For building height, the standard deviation of building height had a significant positive correlation with PM2.5 all year round. For building density, the building count density showed a significant positive correlation with PM2.5 in general, with the bandwidth in winter and autumn smaller than in spring and summer. The building plan area fraction exerted both positive and negative influences on PM2.5, dependent on season and location. The bandwidth of it gradually increased from spring to winter, with the effect changing from local to regional scale. For building volume, the floor area ratio showed a significant negative correlation with PM2.5 in winter and autumn, and a localized effect was found, especially in winter. The findings of this study provide practical implications for urban planning and policy making to mitigate PM2.5 pollution in the rapidly urbanizing regions.

show abstract

Section: Discussionmentioning

confidence: 99%

Exploring the relationships between 3D urban landscape patterns and PM_2.5 pollution using the multiscale geographic weighted regression model

Duan,

Cao,

Wang

et al. 2024

Progress in Physical Geography: Earth and Environment

View full text Add to dashboard Cite

show abstract

“…The trend changes during 2007-2020 to decreasing PM2.5 concentrations a ributed to air pollution control policies enforced in the 11th, 12th, and 13th national Five-Year-Plans during 2005-2020. Zhao et al [21] conducted a deep learning simulation for investigating the effects of urban land use and meteorological conditions on PM2.5 concentration. The study field covers all of Wuhan, which is an industrial city in China, and the data in 2016 are collected.…”

Section: Natural and Anthropogenic Factors Affecting Air Qualitymentioning

confidence: 99%

Mining Associations between Air Quality and Natural and Anthropogenic Factors

Yin

2024

Sustainability

View full text Add to dashboard Cite

The urbanization and industrialization of human society boost the socioeconomic growth but yet inevitably result in unprecedented damages to environment and organisms. One of the threats is the air pollution produced from anthropogenic activities. Moreover, the pollution concentrates longer in certain meteorological phenomena and exacerbates the impact on nature species and human health. This paper presents an association mining approach to identify the influential factors which result in a high volume of air pollution concentration, in particular, the particulate matter with aerodynamic diameter ≤ 2.5 μm (PM2.5). Since the literature showed that the identified factors are location and spatial-scale dependent, we chose a basin geography, Puli township, Taiwan, and inferred the association relationships with two different-scaled monitoring stations. The government-built supersite at Puli estimates the PM2.5 concentration for the entire township of the area around 150 km2, while the participatory microsites monitor air quality in a smaller region of a hundred thousand square meters. Our research was conducted with relevant data during 2017–2019. The mining result has unique findings as compared to the literature. The relative humidity, precipitation, wind speed and direction, which were identified as major factors in many previous studies, have less impact on air quality of our studied field than temperature and atmospheric pressure. The remarkable distinction is mainly attributed to the special weather patterns of basin geography. We investigated the impact of all national festivals and identified the most significant ones. The probability of observing PM2.5 concentrations greater than 35 μg/m3 in the activity hours of New Year’s Eve is 50% which is significantly greater than 11.74%, the probability of observing the same concentration range over all days in the investigated years, while the Tomb Sweeping Day (TSD) has a varying impact on air quality depending on the order of the TSD date within the long holiday. The increase of PM2.5 concentration is remarkably more significant if the TSD is the last day in the long holiday than if it is the middle day. This finding can be taken into consideration when the government agent makes schedules for national festivals. Finally, it was learned in our study that different landmarks and land uses have various significant impacts on micro-scale air quality. The microsites monitor high PM2.5 concentrations at particular landmarks with a greater confidence than the mean confidence over all microsites. These pollution-associated landmarks with the confidence ranked from highest to lowest are night markets, crossroads, paper mills, temples, and highway exits. It is worth noting that the PM2.5 increase contributed by temples is negligible, which may be attributed to the citizen action for promoting reduction in joss paper and incense stick burning. The land uses have diverse impacts on air quality. Anthropogenic activities contribute higher PM2.5 concentrations in business districts and residential areas. The PM2.5 concentration monitored at high lands and agricultural lands is lower than the overall background due to fewer mass gathering and combustion activities in these land uses.

show abstract

“…They compared seven machine learning algorithms for modelling the nonlinear relationship between the building morphology and the outdoor environments of 150 workers' villages in Shanghai [ 13 ]. Zhao et al employed a deep learning simulation method to explore the effects of land use types and density on the spatial distribution of PM2.5 pollutants in the city of Wuhan [ 14 ]. Kabošová et al introduced and tested an environment-driven design technique at the urban and architectural scale.…”

Section: Introductionmentioning

confidence: 99%

Data-mining framework for in-depth quantitative study of influences on low-wind-velocity area from morphological parameters of cuboid-form buildings

Guo,

Song,

Chu

et al. 2024

Heliyon

View full text Add to dashboard Cite

Investigate the effects of urban land use on PM2.5 concentration: An application of deep learning simulation

Cited by 15 publications

References 70 publications

Exploring the relationships between 3D urban landscape patterns and PM_2.5 pollution using the multiscale geographic weighted regression model

Exploring the relationships between 3D urban landscape patterns and PM_2.5 pollution using the multiscale geographic weighted regression model

Mining Associations between Air Quality and Natural and Anthropogenic Factors

Data-mining framework for in-depth quantitative study of influences on low-wind-velocity area from morphological parameters of cuboid-form buildings

Contact Info

Product

Resources

About

Investigate the effects of urban land use on PM2.5 concentration: An application of deep learning simulation

Cited by 15 publications

References 70 publications

Exploring the relationships between 3D urban landscape patterns and PM2.5 pollution using the multiscale geographic weighted regression model

Exploring the relationships between 3D urban landscape patterns and PM2.5 pollution using the multiscale geographic weighted regression model

Mining Associations between Air Quality and Natural and Anthropogenic Factors

Data-mining framework for in-depth quantitative study of influences on low-wind-velocity area from morphological parameters of cuboid-form buildings

Contact Info

Product

Resources

About

Exploring the relationships between 3D urban landscape patterns and PM_2.5 pollution using the multiscale geographic weighted regression model

Exploring the relationships between 3D urban landscape patterns and PM_2.5 pollution using the multiscale geographic weighted regression model