Machine Learning Modeling Reveals Divergent Air Pollutant Responses to Stringent Emission Controls in the Yangtze River Delta Region

Ozone (O<sub>3</sub>) and fine particulate matter (PM<sub>2.5</sub>) are critical atmospheric pollutants whose complex chemical coupling presents significant challenges for multi-pollutant control strategies. This study investigated the spatiotemporal variations and driving m...

Full description

Saved in:
Bibliographic Details
Main Authors: Qiufang Yao, Linhao Wang, Wenjing Qiu, Yutong Shi, Qi Xu, Yanping Xiao, Jiacheng Zhou, Shilong Li, Haobin Zhong, Jinsong Liu
Format: Article
Language:English
Published: MDPI AG 2025-06-01
Series:Atmosphere
Subjects:
Online Access:https://www.mdpi.com/2073-4433/16/6/710
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849434029589266432
author Qiufang Yao
Linhao Wang
Wenjing Qiu
Yutong Shi
Qi Xu
Yanping Xiao
Jiacheng Zhou
Shilong Li
Haobin Zhong
Jinsong Liu
author_facet Qiufang Yao
Linhao Wang
Wenjing Qiu
Yutong Shi
Qi Xu
Yanping Xiao
Jiacheng Zhou
Shilong Li
Haobin Zhong
Jinsong Liu
author_sort Qiufang Yao
collection DOAJ
description Ozone (O<sub>3</sub>) and fine particulate matter (PM<sub>2.5</sub>) are critical atmospheric pollutants whose complex chemical coupling presents significant challenges for multi-pollutant control strategies. This study investigated the spatiotemporal variations and driving mechanisms of O<sub>3</sub> and PM<sub>2.5</sub> in Jiaxing, China, during different COVID-19 lockdown periods from November 2019 to January 2024. Using high-resolution monitoring data, random forest modeling, and HYSPLIT backward trajectory analysis, we quantified the relative contributions of anthropogenic emissions, meteorological conditions, and regional transport to the formation and variation of O<sub>3</sub> and PM<sub>2.5</sub> concentrations. The results revealed a distinct inverse relationship between O<sub>3</sub> and PM<sub>2.5</sub>, with meteorologically normalized PM<sub>2.5</sub> decreasing significantly (−5.0 μg/m<sup>3</sup> compared to the pre-lockdown baseline of 0.6 μg/m<sup>3</sup>), while O<sub>3</sub> increased substantially (15.2 μg/m<sup>3</sup> compared to the baseline of 5.3 μg/m<sup>3</sup>). Partial dependency analysis revealed that PM<sub>2.5</sub>-O<sub>3</sub> relationships evolved from linear to non-linear patterns across lockdown periods, while NO<sub>2</sub>-O<sub>3</sub> interactions indicated shifts from VOC-limited to NO<sub>x</sub>-limited regimes. Regional transport patterns exhibited significant temporal variations, with source regions shifting from predominantly northern areas pre-lockdown to more diverse directional contributions afterward. Notably, the partial lockdown period demonstrated the most balanced pollution control outcomes, maintaining reduced PM<sub>2.5</sub> levels while avoiding O<sub>3</sub> increases. These findings provide critical insights for developing targeted multi-pollutant control strategies in the Yangtze River Delta region and similar urban environments.
format Article
id doaj-art-fbbb374c119a435e84cd5849c25ea202
institution Kabale University
issn 2073-4433
language English
publishDate 2025-06-01
publisher MDPI AG
record_format Article
series Atmosphere
spelling doaj-art-fbbb374c119a435e84cd5849c25ea2022025-08-20T03:26:49ZengMDPI AGAtmosphere2073-44332025-06-0116671010.3390/atmos16060710Machine Learning Modeling Reveals Divergent Air Pollutant Responses to Stringent Emission Controls in the Yangtze River Delta RegionQiufang Yao0Linhao Wang1Wenjing Qiu2Yutong Shi3Qi Xu4Yanping Xiao5Jiacheng Zhou6Shilong Li7Haobin Zhong8Jinsong Liu9School of Advanced Materials Engineering, Jiaxing Nanhu University, Jiaxing 314001, ChinaSchool of Advanced Materials Engineering, Jiaxing Nanhu University, Jiaxing 314001, ChinaSchool of Advanced Materials Engineering, Jiaxing Nanhu University, Jiaxing 314001, ChinaSchool of Advanced Materials Engineering, Jiaxing Nanhu University, Jiaxing 314001, ChinaSchool of Advanced Materials Engineering, Jiaxing Nanhu University, Jiaxing 314001, ChinaSchool of Advanced Materials Engineering, Jiaxing Nanhu University, Jiaxing 314001, ChinaSchool of Advanced Materials Engineering, Jiaxing Nanhu University, Jiaxing 314001, ChinaSchool of Advanced Materials Engineering, Jiaxing Nanhu University, Jiaxing 314001, ChinaSchool of Advanced Materials Engineering, Jiaxing Nanhu University, Jiaxing 314001, ChinaSchool of Advanced Materials Engineering, Jiaxing Nanhu University, Jiaxing 314001, ChinaOzone (O<sub>3</sub>) and fine particulate matter (PM<sub>2.5</sub>) are critical atmospheric pollutants whose complex chemical coupling presents significant challenges for multi-pollutant control strategies. This study investigated the spatiotemporal variations and driving mechanisms of O<sub>3</sub> and PM<sub>2.5</sub> in Jiaxing, China, during different COVID-19 lockdown periods from November 2019 to January 2024. Using high-resolution monitoring data, random forest modeling, and HYSPLIT backward trajectory analysis, we quantified the relative contributions of anthropogenic emissions, meteorological conditions, and regional transport to the formation and variation of O<sub>3</sub> and PM<sub>2.5</sub> concentrations. The results revealed a distinct inverse relationship between O<sub>3</sub> and PM<sub>2.5</sub>, with meteorologically normalized PM<sub>2.5</sub> decreasing significantly (−5.0 μg/m<sup>3</sup> compared to the pre-lockdown baseline of 0.6 μg/m<sup>3</sup>), while O<sub>3</sub> increased substantially (15.2 μg/m<sup>3</sup> compared to the baseline of 5.3 μg/m<sup>3</sup>). Partial dependency analysis revealed that PM<sub>2.5</sub>-O<sub>3</sub> relationships evolved from linear to non-linear patterns across lockdown periods, while NO<sub>2</sub>-O<sub>3</sub> interactions indicated shifts from VOC-limited to NO<sub>x</sub>-limited regimes. Regional transport patterns exhibited significant temporal variations, with source regions shifting from predominantly northern areas pre-lockdown to more diverse directional contributions afterward. Notably, the partial lockdown period demonstrated the most balanced pollution control outcomes, maintaining reduced PM<sub>2.5</sub> levels while avoiding O<sub>3</sub> increases. These findings provide critical insights for developing targeted multi-pollutant control strategies in the Yangtze River Delta region and similar urban environments.https://www.mdpi.com/2073-4433/16/6/710machine learningair pollution controlpartial dependency analysisregional transportYangtze River Delta region
spellingShingle Qiufang Yao
Linhao Wang
Wenjing Qiu
Yutong Shi
Qi Xu
Yanping Xiao
Jiacheng Zhou
Shilong Li
Haobin Zhong
Jinsong Liu
Machine Learning Modeling Reveals Divergent Air Pollutant Responses to Stringent Emission Controls in the Yangtze River Delta Region
Atmosphere
machine learning
air pollution control
partial dependency analysis
regional transport
Yangtze River Delta region
title Machine Learning Modeling Reveals Divergent Air Pollutant Responses to Stringent Emission Controls in the Yangtze River Delta Region
title_full Machine Learning Modeling Reveals Divergent Air Pollutant Responses to Stringent Emission Controls in the Yangtze River Delta Region
title_fullStr Machine Learning Modeling Reveals Divergent Air Pollutant Responses to Stringent Emission Controls in the Yangtze River Delta Region
title_full_unstemmed Machine Learning Modeling Reveals Divergent Air Pollutant Responses to Stringent Emission Controls in the Yangtze River Delta Region
title_short Machine Learning Modeling Reveals Divergent Air Pollutant Responses to Stringent Emission Controls in the Yangtze River Delta Region
title_sort machine learning modeling reveals divergent air pollutant responses to stringent emission controls in the yangtze river delta region
topic machine learning
air pollution control
partial dependency analysis
regional transport
Yangtze River Delta region
url https://www.mdpi.com/2073-4433/16/6/710
work_keys_str_mv AT qiufangyao machinelearningmodelingrevealsdivergentairpollutantresponsestostringentemissioncontrolsintheyangtzeriverdeltaregion
AT linhaowang machinelearningmodelingrevealsdivergentairpollutantresponsestostringentemissioncontrolsintheyangtzeriverdeltaregion
AT wenjingqiu machinelearningmodelingrevealsdivergentairpollutantresponsestostringentemissioncontrolsintheyangtzeriverdeltaregion
AT yutongshi machinelearningmodelingrevealsdivergentairpollutantresponsestostringentemissioncontrolsintheyangtzeriverdeltaregion
AT qixu machinelearningmodelingrevealsdivergentairpollutantresponsestostringentemissioncontrolsintheyangtzeriverdeltaregion
AT yanpingxiao machinelearningmodelingrevealsdivergentairpollutantresponsestostringentemissioncontrolsintheyangtzeriverdeltaregion
AT jiachengzhou machinelearningmodelingrevealsdivergentairpollutantresponsestostringentemissioncontrolsintheyangtzeriverdeltaregion
AT shilongli machinelearningmodelingrevealsdivergentairpollutantresponsestostringentemissioncontrolsintheyangtzeriverdeltaregion
AT haobinzhong machinelearningmodelingrevealsdivergentairpollutantresponsestostringentemissioncontrolsintheyangtzeriverdeltaregion
AT jinsongliu machinelearningmodelingrevealsdivergentairpollutantresponsestostringentemissioncontrolsintheyangtzeriverdeltaregion