Preprints
https://doi.org/10.5194/egusphere-2024-2776
https://doi.org/10.5194/egusphere-2024-2776
25 Nov 2024
 | 25 Nov 2024
Status: this preprint is open for discussion and under review for Atmospheric Chemistry and Physics (ACP).

Technical note: Reconstructing surface missing aerosol elemental carbon data in long-term series with ensemble learning

Qingxiao Meng, Yunjiang Zhang, Sheng Zhong, Jie Fang, Lili Tang, Yongcai Rao, Minfeng Zhou, Jian Qiu, Xiaofeng Xu, Jean-Eudes Petit, Olivier Favez, and Xinlei Ge

Abstract. Ground-based measurements of elemental carbon (EC) – classified under thermal-optical methods and considered as a surrogate for black carbon – are essential for assessing air quality and evaluating climate impacts. However, data gaps caused by technical challenges impede comprehensive analyses of long-term trends. This study proposes an ensemble learning method to address these challenges. The model uses readily accessible ground observation air pollutant data as proxies for EC-related tracers, along with meteorological parameters, to enhance prediction accuracy. It integrates outputs from Gradient Boosting Regression Trees, eXtreme Gradient Boosting, and Random Forest models, combining them through ridge regression to produce robust predictions. We applied this approach to reconstruct hourly EC concentrations from 2013 to 2023 for four cities in Eastern China, filling 45–79 % of missing data and improving prediction performance by 8–17 % compared to individual models. Over the 11-year period, EC exhibited an overall decline (-0.20 to -0.14 µg m-3 a-1), with a more significant decline from 2013 to 2020 (-0.24 to -0.15 µg m-3 a-1) from 3.26 µg m-3 to 1.59 µg m-3, followed by a noticeable slowdown from 2020 to 2023 (-0.12 to -0.04 µg m-3 a-1). Additionally, a fixed emission approximation method based on ensemble learning is proposed to quantitatively analyze the drivers of long-term EC trends. The analysis reveals that anthropogenic emission controls were the predominant contributors, accounting for approximately 92 % of the changes in EC trends from 2013 to 2020. However, their influence weakened post-2020, contributing approximately 80 %. These findings highlight that while China's Clean Air Actions implemented since 2013 have significantly reduced black carbon concentrations, sustained and enhanced strategies are still necessary to further mitigate black carbon pollution in the country.

Publisher's note: Copernicus Publications remains neutral with regard to jurisdictional claims made in the text, published maps, institutional affiliations, or any other geographical representation in this preprint. The responsibility to include appropriate place names lies with the authors.
Qingxiao Meng, Yunjiang Zhang, Sheng Zhong, Jie Fang, Lili Tang, Yongcai Rao, Minfeng Zhou, Jian Qiu, Xiaofeng Xu, Jean-Eudes Petit, Olivier Favez, and Xinlei Ge

Status: open (until 11 Jan 2025)

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse
Qingxiao Meng, Yunjiang Zhang, Sheng Zhong, Jie Fang, Lili Tang, Yongcai Rao, Minfeng Zhou, Jian Qiu, Xiaofeng Xu, Jean-Eudes Petit, Olivier Favez, and Xinlei Ge
Qingxiao Meng, Yunjiang Zhang, Sheng Zhong, Jie Fang, Lili Tang, Yongcai Rao, Minfeng Zhou, Jian Qiu, Xiaofeng Xu, Jean-Eudes Petit, Olivier Favez, and Xinlei Ge

Viewed

Total article views: 118 (including HTML, PDF, and XML)
HTML PDF XML Total Supplement BibTeX EndNote
97 16 5 118 16 1 1
  • HTML: 97
  • PDF: 16
  • XML: 5
  • Total: 118
  • Supplement: 16
  • BibTeX: 1
  • EndNote: 1
Views and downloads (calculated since 25 Nov 2024)
Cumulative views and downloads (calculated since 25 Nov 2024)

Viewed (geographical distribution)

Total article views: 116 (including HTML, PDF, and XML) Thereof 116 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 
Latest update: 13 Dec 2024
Download
Short summary
We developed a new method to reconstruct missing elemental carbon (EC) data in four Chinese cities from 2013 to 2023. Using machine learning, we accurately filled data gaps and introduced a new approach to analyze EC trends. Our findings reveal a significant decline in EC due to stricter pollution controls, though this slowed after 2020. This study provides a versatile framework for addressing data gaps and supports strategies to reduce urban air pollution and its climate impacts.