Classification and quantification of low-visibility events using deep learning over eastern China
- 1Zhejiang University (Hangzhou, China)
Abstract
Low-visibility events (LVEs) threaten transportation safety and human health, yet accurately identifying them at a regional scale remains challenging. To address this, this study introduces a unified convolutional neural network (CNN) framework that integrates the geostationary satellite, meteorology, and fine particulate matter (PM 2.5 ) observation data to identify all types of LVEs. The model can not only produce the spatiotemporal distribution of LVEs, including land and sea fog, but also quantify the intensity of LVEs linked to visibility reduction. By incorporating PM 2.5 , the polluted fog-haze over land can be discriminated from clean fog. Based on the model, we are able to investigate the environmental policy to reduce fog-haze and the corresponding population exposure. Over eastern China, a 20 % reduction of overall PM 2.5 can reduce the fog-haze area by 43 % in winter. However, the corresponding population exposure is reduced less effectively by 15 %, because the most populated region collocates with the most polluted region, where a further reduction of PM 2.5 by over 40 % is required to effectively reduce its population exposure. Here, the classified and quantified LVEs, along with the established relationship with pollution, explicitly guide the air-quality policy for the co-benefits of improving air visibility and human health.
Versions
Related
- Higher prevalence of rising climate-driven snowmelt potential of rain-on-snow events in the Eastern Continental US
- Advancing Near-Term Water Quality Forecasting with Explainable Machine Learning and Probabilistic Uncertainty Quantification
- Deep learning reveals severe shelterbelt degradation in eastern Ukraine due to the war
- Machine learning-based classification of Hyrcanian forests using PRISMA data
- Who speaks for sustainability transformation: Gendered visibility at Taiwan’s sustainability forums
BibTeX
@article{liang2026classification,
title = {{Classification and quantification of low-visibility events using deep learning over eastern China}},
author = {Yuting Liang and Shitong Zhao and Dantong Liu and Changhao Wu and Li Yi and Xingcan Jia and Honghui Xu and Jiankan Wang},
journal = {Atmospheric Chemistry and Physics},
year = {2026},
month = oct,
doi = {10.5194/acp-26-15003-2026},
url = {https://doi.org/10.5194/acp-26-15003-2026},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - Classification and quantification of low-visibility events using deep learning over eastern China
AU - Yuting Liang
AU - Shitong Zhao
AU - Dantong Liu
AU - Changhao Wu
AU - Li Yi
AU - Xingcan Jia
AU - Honghui Xu
AU - Jiankan Wang
PY - 2026
DA - 2026/10/26
JO - Atmospheric Chemistry and Physics
DO - 10.5194/acp-26-15003-2026
UR - https://doi.org/10.5194/acp-26-15003-2026
AB - Low-visibility events (LVEs) threaten transportation safety and human health, yet accurately identifying them at a regional scale remains challenging. To address this, this study introduces a unified convolutional neural network (CNN) framework that integrates the geostationary satellite, meteorology, and fine particulate matter (PM 2.5 ) observation data to identify all types of LVEs. The model can not only produce the spatiotemporal distribution of LVEs, including land and sea fog, but also quantify the intensity of LVEs linked to visibility reduction. By incorporating PM 2.5 , the polluted fog-haze over land can be discriminated from clean fog. Based on the model, we are able to investigate the environmental policy to reduce fog-haze and the corresponding population exposure. Over eastern China, a 20 % reduction of overall PM 2.5 can reduce the fog-haze area by 43 % in winter. However, the corresponding population exposure is reduced less effectively by 15 %, because the most populated region collocates with the most polluted region, where a further reduction of PM 2.5 by over 40 % is required to effectively reduce its population exposure. Here, the classified and quantified LVEs, along with the established relationship with pollution, explicitly guide the air-quality policy for the co-benefits of improving air visibility and human health.
SN - 1680-7324
SN - 1680-7316
ER -