Estimation of Atmospheric PM<sub>10</sub> Concentration in China Using an Interpretable Deep Learning Model and Top‐of‐the‐Atmosphere Reflectance Data From China’s New Generation Geostationary Meteorological Satellite, FY‐4A

Chen, Bin; Song, Zhihao; Huang, Jianping; Zhang, Peng; Hu, Xiuqing; Zhang, Xingying; Guan, Xiaodan; Ge, Jinming; Zhou, Xingzhao

doi:10.1029/2021jd036393

Cited by 22 publications

(9 citation statements)

References 93 publications

(113 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The maximum frequencies of dust aerosols in BTH and GZ, reaching approximately 10%, were observed at 2 and 4 km, respectively. Many studies have shown that dust aerosols originating from Northwest China and Mongolia can be transported to BTH and GZ (Huang et al., 2008), and the long‐range transport dust is one of the important contributors to PM10 during haze periods in these regions (Chen, Song, Huang, et al., 2022).…”

Section: Resultsmentioning

confidence: 99%

“…Due to the large-scale transmission of aerosols from Mongolia and the Gobi Desert west of mainland China, the occurrence frequency of dust aerosols in Beijing is also high (Zhang et al, 2009). Previous studies have demonstrated that long-distance transport of aerosols can lead to significant variations in the aerosol optical properties and distribution (Chen et al, 2022;Han et al, 2022;McKendry et al, 2011;Ramanathan & Feng, 2009).…”

mentioning

confidence: 99%

See 1 more Smart Citation

Analysis of Long‐Term Trends in the Vertical Distribution and Transport Paths of Atmospheric Aerosols in Typical Regions of China Using 15 Years of CALIOP Data

Chen

Huang

et al. 2023

JGR Atmospheres

Self Cite

View full text Add to dashboard Cite

Long‐range transport and vertical distribution of aerosols are important factors for assessing the uncertainty in aerosol radiative forcing. This paper reveals the vertical distribution and trends of aerosol optical properties in China using 15 years of Cloud‐Aerosol Lidar with Orthogonal Polarization (CALIOP) data. The Hybrid Single‐Particle Lagrangian integrated trajectory model was used to analyze the transport and trends of aerosols in the layer with the highest occurrence frequencies of dust, polluted dust, polluted continental and elevated smoke aerosols. The results indicated that (a) there were significant regional and seasonal differences in the vertical distribution of aerosols. The aerosol optical depth (AOD) trend in a given region depends on the changes in the aerosol type with the highest frequency and the layer corresponding to the largest AOD in the vertical profile. The frequency of polluted dust aerosols was the highest in Beijing‐Tianjin‐Hebei (BTH) and Central China. The considerable decrease in the 0–2 km AOD led to a significant trend of the column AOD. (b) The changes of AOD and main aerosol types in a region are also affected by the changes of aerosol sources and long‐range transport pathways. In the BTH, dust aerosols originated from the Mongolian Plateau, accounting for 57.88% of the total trajectories. The Pearl River Delta was dominated by elevated smoke aerosols, with trajectories mainly originating from the Myanmar and Vietnam, accounting for 27.38% and 29.59%, respectively. The trend of 15‐year backward trajectories of dust aerosols on the Tibetan Plateau indicated that the trajectory from India is increasing.

show abstract

Section: Resultsmentioning

confidence: 99%

mentioning

confidence: 99%

Analysis of Long‐Term Trends in the Vertical Distribution and Transport Paths of Atmospheric Aerosols in Typical Regions of China Using 15 Years of CALIOP Data

Chen

Huang

et al. 2023

JGR Atmospheres

Self Cite

View full text Add to dashboard Cite

show abstract

“…Using MODIS images and the deep belief network, Imani predicted the PM-suspended particles map for small places (Imani, 2021). In another study, Chen et al estimated PM10 values using a deep learning model and superior atmospheric re ectance data from a new geostationary meteorological satellite (Chen et al, 2022). Also, Shen et al developed a deep model to predict PM 2.5 directly using high atmospheric re ectance satellites (Shen et al, 2018).…”

Section: Introductionmentioning

confidence: 99%

Prediction of hourly PM10 concentration through a hybrid deep learning-based method

Molaei

Salajegheh

Khosravi

et al. 2023

Preprint

View full text Add to dashboard Cite

Air pollution can have detrimental effects on human health as well as the environment. Particulate Matter (PM), as a global issue, is a type of air pollution that consists of small particles suspended in the air. Therefore, it is crucial to estimate and monitor levels of PM in the air in order to protect public health and the environment. This study proposed a novel hybrid method to apply the capability of two various deep learning models, namely, the encoder-decoder convolutional neural network and the Long Short-Term Memory (LSTM) model for PM10 prediction. The first model was utilized as a data argumentation method to enhance dataset diversity, and the LSTM model employed meteorological parameters and spatiotemporal factors to estimate the PM10 levels. The proposed technique achieved performance resulting in a coefficient of determination value of 0.88 and a mean absolute error value of 7.24. The results confirm that the developed hybrid method as an effective tool of PM prediction can be used to inform decision-making about policies and actions to reduce PM levels.

show abstract

“…Soluble aerosols such as sulfate, nitrate, and sea salt, and coarse aerosols such as dust, which can act as CCN, have important contributions to cloud/fog formation and precipitation [ 26 , 27 , 28 , 29 ], and is a breakthrough in understanding the transformation of LVEs from a microscopic perspective. CCN activation is generally affected by aerosol size distribution [ 30 ], chemical composition [ 31 , 32 ], aging [ 33 ], and mixing state [ 34 ].…”

Section: Introductionmentioning

confidence: 99%

Fog–Haze Transition and Drivers in the Coastal Region of the Yangtze River Delta

Lyu

Gao

Peng

et al. 2022

IJERPH

View full text Add to dashboard Cite

Low-visibility events (LVEs) are severe weather phenomena that are closely linked with anthropogenic pollution, which negatively affects traffic, air quality, human health, and the environment. This study conducted a two-month (from October to December 2019) continuous measurement campaign on Chongming Island in Shanghai to characterize the LVEs transition and its drivers. The LVEs accounted for 38% of the time during the campaign, of which mist accounted for 14%, fog–haze for 13%, haze for 6%, and fog for 5%. The fog and mist mainly occurred from midnight to early morning, while haze mostly occurred during the daytime. Different LVEs were interdependent and transitioned from one to another. Fog generally turned into haze after sunrise, while haze turned into fog after sunset. Their formation and evolution were caused by the combined impacts of meteorological conditions and aerosol particles. It was found that temperature difference was the dominant meteorological factor driving the evolution of LVEs. Within the short term, cooling led to a greater increase in relative humidity than humidification. Radiative cooling during the night promoted the formation of fog and mist. During fog and mist events, cloud condensation nuclei (CCN) were mainly internally mixed due to the impact of fog droplet removal and aqueous/heterogeneous aerosol reactions occurring under high humidity. Increased CCN concentration appeared to increase the fog droplet number and liquid water content in fog events. Overall, conditions of high humidity and high particle loading were conducive to LVEs, whereas conditions of sufficient water vapor at a low particle level and sufficient particles at a low humidity level also caused LVEs. This study provided insights into LVEs classification, evolution scheme, and aerosol roles from a micro point of view. The findings could be useful for improving forecasts of local radiative fog and other LVEs.

show abstract

Estimation of Atmospheric PM₁₀ Concentration in China Using an Interpretable Deep Learning Model and Top‐of‐the‐Atmosphere Reflectance Data From China’s New Generation Geostationary Meteorological Satellite, FY‐4A

Abstract: Atmospheric particulate matter with an aerodynamic diameter less than 10 μm (PM 10 ) has a great impact on global environmental (

Cited by 22 publications

References 93 publications

Analysis of Long‐Term Trends in the Vertical Distribution and Transport Paths of Atmospheric Aerosols in Typical Regions of China Using 15 Years of CALIOP Data

Analysis of Long‐Term Trends in the Vertical Distribution and Transport Paths of Atmospheric Aerosols in Typical Regions of China Using 15 Years of CALIOP Data

Prediction of hourly PM10 concentration through a hybrid deep learning-based method

Fog–Haze Transition and Drivers in the Coastal Region of the Yangtze River Delta

Contact Info

Product

Resources

About

Estimation of Atmospheric PM10 Concentration in China Using an Interpretable Deep Learning Model and Top‐of‐the‐Atmosphere Reflectance Data From China’s New Generation Geostationary Meteorological Satellite, FY‐4A

Abstract: Atmospheric particulate matter with an aerodynamic diameter less than 10 μm (PM 10 ) has a great impact on global environmental (

Cited by 22 publications

References 93 publications

Analysis of Long‐Term Trends in the Vertical Distribution and Transport Paths of Atmospheric Aerosols in Typical Regions of China Using 15 Years of CALIOP Data

Analysis of Long‐Term Trends in the Vertical Distribution and Transport Paths of Atmospheric Aerosols in Typical Regions of China Using 15 Years of CALIOP Data

Prediction of hourly PM10 concentration through a hybrid deep learning-based method

Fog–Haze Transition and Drivers in the Coastal Region of the Yangtze River Delta

Contact Info

Product

Resources

About

Estimation of Atmospheric PM₁₀ Concentration in China Using an Interpretable Deep Learning Model and Top‐of‐the‐Atmosphere Reflectance Data From China’s New Generation Geostationary Meteorological Satellite, FY‐4A