Evaluating Emergency Emission Controls During an Unprecedented Regional Haze Event Using Causal Machine Learning
Environmental Science & Technology · 10.11.2026 · 60 (44) · 31908-31917
DOI: 10.1021/acs.est.6c12991 ↗Kurz gefasst
Fachartikel in der Zeitschrift Environmental Science & Technology, online erschienen am 23.10.2026. Verfasst von Weizhao Liang und 8 weiteren Autor:innen. Beteiligte Einrichtung: Key Laboratory of Urban Air Particulate Pollution Prevention and Control of Ministry of Ecology and Environment, College of Environmental Science and…. Hauptthemen laut MEDLINE: Machine Learning, Air Pollution. Die Arbeit nennt 53 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: Fundamental Research Funds for the Central Universities, Natural Science Foundation of Tianjin City, National Natural Science Foundation of China (NSFC).
Abstract (Originalsprache)
Emergency emission controls are widely implemented to mitigate severe haze, yet their effectiveness is difficult to disentangle from meteorological variability and concurrent changes in activities. Here, we develop a three-step evaluation approach integrating air quality meteorological normalization, augmented synthetic control, and machine-learning prediction to causally quantify intervention-attributable changes in local emission strength and ambient pollutant concentrations. Applied to Shijiazhuang’s unprecedented 45-day “Sharp Sword to Cut Haze” campaign in 2016, the approach revealed that local emission strengths of PM2.5, PM10, SO2, NO2, and CO were reduced by 4.3%, 4.8%, 15.8%, 5.8%, and 15.3%, respectively. Corresponding concentrations fell by 42.1 (14.8%), 47.4 (12.4%), 13.8 (16.6%), 15.8 (15.5%) μg·m–3, and 0.9 mg·m–3 (19.6%). Observation-based PM2.5 source apportionment results independently supported these estimates: contributions from vehicle emissions, steelmaking, and coal combustion were 4.1%, 11.0%, and 21.7% lower, respectively, than during the corresponding period in 2017. Despite stringent controls, PM2.5 averaged 243.2 μg·m–3 during the intervention period. Thus, stringent local controls substantially reduced emissions, but regional transport and unfavorable meteorology partly offset the resulting air quality benefits, highlighting the need for coordinated regional mitigation.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- Key Laboratory of Urban Air Particulate Pollution Prevention and Control of Ministry of Ecology and Environment, College of Environmental Science and Engineering, Nankai University, Tianjin300350, China.
- Tianjin Key Laboratory of Software Experience and Human Computer Interaction, Tianjin300457, China.
- Beijing Municipal Pollution Source Management Center, Beijing100048, China.
- Tianjin Institute of Meteorological Science, Tianjin300074, China.
ORCID-Profile: Qili Dai, Xiaohui Bi, Yinchang Feng
Förderung
- Fundamental Research Funds for the Central Universities
- Natural Science Foundation of Tianjin City
- National Natural Science Foundation of China (NSFC)
Zitieren
APA
Liang, W., Zhu, W., Dai, Q., Feng, R., Ding, J., Liu, B., Bi, X., Zhang, Y., & Feng, Y. (2026). Evaluating Emergency Emission Controls During an Unprecedented Regional Haze Event Using Causal Machine Learning. Environmental Science & Technology, 60(44), 31908-31917. https://doi.org/10.1021/acs.est.6c12991
Vancouver
Liang W, Zhu W, Dai Q, Feng R, Ding J, Liu B, et al. Evaluating Emergency Emission Controls During an Unprecedented Regional Haze Event Using Causal Machine Learning. Environmental Science & Technology. 2026;60(44):31908-31917. doi:10.1021/acs.est.6c12991
BibTeX
@article{Liang2026,
author = {Liang, Weizhao and Zhu, Wubin and Dai, Qili and Feng, Ruihong and Ding, Jing and Liu, Baoshuang and Bi, Xiaohui and Zhang, Yufen and Feng, Yinchang},
title = {Evaluating Emergency Emission Controls During an Unprecedented Regional Haze Event Using Causal Machine Learning},
journal = {Environmental Science & Technology},
year = {2026},
volume = {60},
number = {44},
pages = {31908--31917},
doi = {10.1021/acs.est.6c12991}
}
EUVIMED