Predicting peak daily maximum 8&thinsp;h ozone and linkages to emissions and meteorology in Southern California using machine learning methods (SoCAB-8HR V1.0)

Gao, Ziqi; Wang, Yifeng; Vasilakos, Petros; Ivey, Cesunica E.; Do, Khanh; Russell, Armistead G.

doi:https://doi.org/10.5194/gmd-15-9015-2022

Articles | Volume 15, issue 24

https://doi.org/10.5194/gmd-15-9015-2022

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

https://doi.org/10.5194/gmd-15-9015-2022

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

Articles | Volume 15, issue 24

Model description paper

|

16 Dec 2022

Model description paper |

| 16 Dec 2022

Predicting peak daily maximum 8 h ozone and linkages to emissions and meteorology in Southern California using machine learning methods (SoCAB-8HR V1.0)

Ziqi Gao, Yifeng Wang, Petros Vasilakos, Cesunica E. Ivey, Khanh Do, and Armistead G. Russell

Supplement

https://doi.org/10.5194/gmd-15-9015-2022-supplement

Data sets

Predicting peak daily maximum 8-hour ozone, and linkages to emissions and meteorology, in Southern California using machine learning methods Ziqi Gao https://doi.org/10.5281/zenodo.6892062

Model code and software

Predicting peak daily maximum 8-hour ozone, and linkages to emissions and meteorology, in Southern California using machine learning methods Ziqi Gao https://doi.org/10.5281/zenodo.6892066

Short summary

While the national ambient air quality standard of ozone is based on the 3-year average of the fourth highest 8 h maximum (MDA8) ozone concentrations, these predicted extreme values using numerical methods are always biased low. We built four computational models (GAM, MARS, random forest and SVR) to predict the fourth highest MDA8 ozone in Southern California using precursor emissions, meteorology and climatological patterns. All models presented acceptable performance, with GAM being the best.