Preprints
https://doi.org/10.5194/amt-2021-367
https://doi.org/10.5194/amt-2021-367

  05 Nov 2021

05 Nov 2021

Review status: this preprint is currently under review for the journal AMT.

Ozone formation sensitivity study using machine learning coupled with reactivity of VOC species

Junlei Zhan1, Yongchun Liu1, Wei Ma1, Xin Zhang2, Xuezhong Wang2, Fang Bi2, Yujie Zhang2, Zhenhai Wu2, and Hong Li2 Junlei Zhan et al.
  • 1Aerosol and Haze Laboratory, Advanced Innovation Center for Soft Matter Science and Engineering, Beijing University of Chemical Technology, Beijing 100029, China
  • 2State Key Laboratory of Environmental Criteria and Risk Assessment, Chinese Research Academy of Environmental Sciences, Beijing 100012, China

Abstract. The formation of ground-level ozone (O3) is dependent on both atmospheric chemical processes and meteorological factors. Traditional models have difficulty assessing O3 formation sensitivity in a timely manner due to the limitations of flexibility and computational efficiency. In this study, a random forest (RF) model coupled with the reactivity of volatile organic compound (VOC) species was used to investigate the O3 formation sensitivity in Beijing from 2014 to 2016, and evaluate the relative importance (RI) of chemical and meteorological factors to O3 formation. The results showed that the O3 prediction performance using initial concentrations of VOC species (R2 = 0.87) was better than that using total VOCs (TVOCs) concentrations (R2 = 0.77). Meanwhile, the RIs of VOC species correlated well with their O3 formation potentials (OFPs). O3 formation presented a negative response to NOx, PM2.5 and relative humidity, and a positive response to temperature, solar radiation and VOCs. The O3 isopleth curves calculated by the RF model were generally comparable with those calculated by the box model. O3 formation shifted from a VOC-limited regime to a transition regime from 2014 to 2016. This study demonstrates that the RF model coupled with the initial concentrations of VOC species could provide an accurate, flexible, and computationally efficient approach for O3 sensitivity analysis.

Junlei Zhan et al.

Status: open (until 26 Dec 2021)

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse
  • RC1: 'Comment on amt-2021-367', Anonymous Referee #1, 13 Nov 2021 reply

Junlei Zhan et al.

Junlei Zhan et al.

Viewed

Total article views: 402 (including HTML, PDF, and XML)
HTML PDF XML Total Supplement BibTeX EndNote
297 101 4 402 23 0 5
  • HTML: 297
  • PDF: 101
  • XML: 4
  • Total: 402
  • Supplement: 23
  • BibTeX: 0
  • EndNote: 5
Views and downloads (calculated since 05 Nov 2021)
Cumulative views and downloads (calculated since 05 Nov 2021)

Viewed (geographical distribution)

Total article views: 398 (including HTML, PDF, and XML) Thereof 398 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 
Latest update: 08 Dec 2021
Download
Short summary
Our study investigated the O3 formation sensitivity in Beijing using a random forest model coupled with the reactivity of VOC species. Results found that random forest accurately predicted O3 concentration when initial VOCs were considered, and relative importance correlated well with O3 formation potential. The O3 isopleth curves calculated by the random forest model were generally comparable with those calculated by the box model.