Quantification of COVID-19 impacts on NO₂ and O₃: Systematic model selection and hyperparameter optimization on AI-based meteorological-normalization methods

Wong, Yong Jie and Ali Yeganeh and Chia, Min Yan and Shiu, Huan Yu and Ooi, Maggie Chel Gee and Chang, Jackson Hian Wui and Yoshihisa Shimizu and Homma Ryosuke and Sophal Try and Ahmed Elbeltagi (2023) Quantification of COVID-19 impacts on NO₂ and O₃: Systematic model selection and hyperparameter optimization on AI-based meteorological-normalization methods. Atmospheric Environment, 301. pp. 1-20. ISSN 1352-2310

Text FULL TEXT.pdf Restricted to Registered users only Download (16MB) | Request a copy

Abstract

Since the unprecedented outbreak of the COVID-19, numerous meteorological-normalization techniques have been developed in lockdown-imposed regions to decouple the impacts of meteorology and emissions on the atmospheric environment. However, the application of normalization techniques in regions without lockdown is limited. In this study, we propose a novel research framework to investigate the observed and meteorological-normalized concentrations of nitrogen dioxide (NO₂) and ozone (O₃) across 62 cities in Taiwan. Four meteorological-normalization techniques, namely, the generalized additive model (GAM), generalized linear model (GLM), gradient boosting machine (GBM), and random forest (RF), were developed, optimized, and compared using meteorological and temporal variables. The models were optimized using a systematic trial-and-error approach for data distribution type in GAM and GLM and a grid-search approach for tree numbers in GBM and RF. Based on the findings, for GLM, the optimal data distribution for both NO₂ and O₃ modeling was Gaussian, whereas for GAM, the optimal data distribution for NO₂ and O₃ simulation was quasi- Gaussian and Poisson, respectively. In contrast, for RF and GBM, the optimized number of trees varied significantly by site, ranging from 10 to 6310. The simulation performance of RF and GBM was better than that of GAM and GLM across Taiwan and the best-performing optimized model was selected to identify changes in NO₂ and O₃ concentrations during COVID-19. Throughout 2020, even in the absence of a lockdown, the daily mean meteorological-normalized NO₂ and O₃ levels across Taiwan decreased by 14.9% and 5.8%, respectively, providing novel insights for sustainable air quality management.

Item Type:	Article
Keyword:	Air quality, COVID-19, Absence of lockdown, Meteorological-normalization
Subjects:	Q Science > QC Physics > QC1-999 Physics > QC851-999 Meteorology. Climatology Including the earth's atmosphere T Technology > TD Environmental technology. Sanitary engineering > TD1-1066 Environmental technology. Sanitary engineering > TD878-894 Special types of environment Including soil pollution, air pollution, noise pollution
Department:	CENTRE > Preparation Centre for Science and Technology
Depositing User:	SITI AZIZAH BINTI IDRIS -
Date Deposited:	03 Sep 2025 10:52
Last Modified:	03 Sep 2025 10:52
URI:	https://eprints.ums.edu.my/id/eprint/45133

Actions (login required)

View Item