Revealing the drivers of surface ozone pollution by explainable machine learning and satellite observations in Hangzhou Bay, China.

Surface ozone (O 3) pollution is an emerging concern in China. Hangzhou Bay (HZB), where the petrochemical industry is clustered, has become one of China's most O 3 polluted areas due to exposure to volatile organic compounds (VOCs) emissions and land-sea breezes. It is urgently need to investigate the multiple drivers of surface O 3 generation in HZB more specifically. The spatial distribution of O 3 trends from April to September (2015–2022) in HZB depicts a general upward trend, with an observed trend of 0.26 μg/m3 a−1, where meteorological factors contribute to 54°% based on the stepwise multiple linear regression (MLR). Ensembled machine learning is more efficient and accurate, especially the Light Gradient Boosting model (LightGBM, R2 = 0.84) outperforms other machine learning algorithms. The Shapley additive explanation (SHAP) technique allows for more in-depth quantification of the contribution of specific factors to O 3 trends. The results of the LightGBM-SHAP algorithm present that solar radiation plays a leading role in O 3 generation. More importantly, stronger solar radiation can still lead to high O 3 concentration accumulation even at lower temperature based on the interaction of SHAP values. For the precursor's emissions, the ratio of formaldehyde-to-NO 2 (HCHO/NO 2) obtained from the Tropospheric Monitoring Instrument (TROPOMI) satellite observations, shows the study area is located in the VOCs-limited and transitional regimes, highlighting that VOCs control is more cost-effective. • Meteorological drivers contribute 54°% to the O 3 increase in HZB. • Stronger solar radiation can lead to high O 3 pollution even at lower temperature. • HZB is in the VOCs-limited and transitional regimes. [ABSTRACT FROM AUTHOR]