Ozone formation sensitivity study using machine learning coupled with the reactivity of volatile organic compound species

Zhan, Junlei; Liu, Yongchun; Ma, Wei; Zhang, Xin; Wang, Xuezhong; Bi, Fang; Zhang, Yujie; Wu, Zhenhai; Li, Hong

doi:https://doi.org/10.5194/amt-15-1511-2022

Articles | Volume 15, issue 5

https://doi.org/10.5194/amt-15-1511-2022

© Author(s) 2022. This work is distributed under
the Creative Commons Attribution 4.0 License.

https://doi.org/10.5194/amt-15-1511-2022

© Author(s) 2022. This work is distributed under
the Creative Commons Attribution 4.0 License.

Articles | Volume 15, issue 5

Research article

|

16 Mar 2022

Research article |

| 16 Mar 2022

Ozone formation sensitivity study using machine learning coupled with the reactivity of volatile organic compound species

Junlei Zhan, Yongchun Liu, Wei Ma, Xin Zhang, Xuezhong Wang, Fang Bi, Yujie Zhang, Zhenhai Wu, and Hong Li

Supplement

https://doi.org/10.5194/amt-15-1511-2022-supplement

Data sets

Ozone formation sensitivity study using machine learning coupled with the reactivity of volatile organic compound species Junlei Zhan, Wei Ma, Yongchun Liu, Xin Zhang, Xuezhong Wang, Fang Bi, Yujie Zhang, Zhenhai Wu, and Hong Li https://doi.org/10.5281/zenodo.6330176

Model code and software

Ozone formation sensitivity study using machine learning coupled with the reactivity of volatile organic compound species Junlei Zhan, Yongchun Liu, Wei Ma, Xin Zhang, Xuezhong Wang, Fang Bi, Yujie Zhang, Zhenhai Wu, and Hong Li https://doi.org/10.5281/zenodo.6327734

Short summary

Our study investigated the O₃ formation sensitivity in Beijing using a random forest model coupled with the reactivity of volatile organic compound (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.