Vol.:(0123456789) 1 3 Environmental Science and Pollution Research https://doi.org/10.1007/s11356-023-29665-5 RESEARCH ARTICLE Assessment of meteorological and air quality drivers of elevated ambient ozone in Beijing via machine learning approach Muhammad Azher Hassan 1  · Muhammad Faheem 2  · Tariq Mehmood 3  · Yihui Yin 4  · Junjie Liu 1 Received: 17 April 2023 / Accepted: 30 August 2023 © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2023 Abstract Over the past few years, surface ozone (O 3 ) pollution has dominated China’s air pollution as particulate matter has decreased. In Beijing, the annual average concentrations of ground-level O 3 from 2015 to 2020 regularly increased from 57.32 to 62.72 μg/m 3 , showing a change of almost 9.4%, with a 1.6% per year increase. The meteorological factors are the primary infuencer of elevated O 3 levels; however, their importance and heterogeneity of variables remain rarely understood. In this study, we used 13 meteorological factors and 6 air quality (AQ) parameters to estimate their infuencing score using the random forest (RF) algorithm to explain and predict ambient O 3 . Among the meteorological variables and overall, both land surface temperature and temperature at 2 m from the surface emerged as the most infuential factors, while NO 2 stood out as the highest infuencing factor from the AQ parameters. Indeed, it is crucial and imperative to reduce the temperature caused by climate change in order to efectively control ambient O 3 levels in Beijing. Overall, meteorological factors alone exhibited a higher coefcient of determination (R 2 ) value of 0.80, compared with AQ variables of 0.58, for the post-lockdown period. In addition, we calculated the number of days O 3 concentration levels exceeded the WHO standard and newly proposed peak-season maximum daily 8-h average (MDA8) O 3 guideline for Beijing. The exceedance number of days from the WHO standard of MDA8 ambient O 3 was observed to be the highest in June, and each studied year crossed peak season guidelines by almost 2 times margin. This study demonstrates the contributions of meteorological variables and AQ parameters in surg- ing ambient O 3 and highlights the importance of future research toward devising an optimum strategy to combat growing O 3 pollution in urban areas. Keywords Tropospheric ozone · Air pollution · Random forest · Ambient pollution trends · Climate efect · Post-lockdown O 3 Introduction Ozone (O 3 ) at the lower troposphere is a secondary air pol- lutant and hazardous greenhouse gas known to cause sig- nifcant damage to people’s health as well as to ecosystems. China’s accelerated industrialization over the past three dec- ades has resulted in unprecedented levels of air pollution and related health issues. Over the past decade, Chinese policy- makers have efectively implemented air pollution control initiatives and approaches like the Clean Air Action Plans reduced notable reductions in primary pollutants including particulate matters (PM x ). However, reducing ambient O 3 to meet the WHO’s target for human health has proven chal- lenging in China and worldwide despite stringent controls on O 3 precursor emissions. In addition, China has a much higher frequency and magnitude of rising O 3 events than other industrial regions (Lu et al. 2018). Responsible Editor: Marcus Schulz * Junjie Liu jjliu@tju.edu.cn 1 Tianjin Key Lab of Indoor Air Environmental Quality Control, School of Environmental Science and Engineering, Tianjin University, Tianjin 300072, China 2 Department of Civil Infrastructure and Environmental Engineering, Khalifa University of Science and Technology, Abu Dhabi, United Arab Emirates 3 Department of Environmental Engineering, Helmholtz Centre for Environmental Research - UFZ, Permoserstr. 15, D-04318 Leipzig, Germany 4 Department of Building Environment and Energy Engineering, The Hong Kong Polytechnic University, Kowloon, Hong Kong SAR, China