Application of machine learning to analyze ozone sensitivity to influencing factors: A case study in Nanjing, China

Abstract

Ground-level ozone (O3) has been an emerging concern in China. Due to its complicated formation mechanisms, understanding the effects of influencing factors is critical for making effective efforts on the pollution control. This study aims to present and demonstrate the practicality of a data-driven technique that applies a machine learning (ML) model coupled with the SHapley Additive exPlanations (SHAP) approach in O3 simulation and sensitivity analysis. Based on hourly measured concentrations of O3 and its major precursors, as well as meteorological factors in a northern area of Nanjing, China, a Light Gradient Boosting Machine (LightGBM) model was established to simulate O3 concentrations in different seasons, and the SHAP approach was applied to conduct in-depth analysis on the impacts of influencing factors on O3 formation. The results indicated a reliable performance of the ML model in simulating O3 concentrations, with the coefficient of determination (R2) between the measured and simulated larger than 0.80, and the impacts of influencing factors were reasonably evaluated by the SHAP approach on both seasonal and diurnal time scales. It was found that although volatile organic compounds (VOCs) and nitrogen oxides (NOx), as well as temperature and relative humidity, were generally the main influencing factors, their sensitivities to O3 formation varied significantly in different seasons and with time of the day. This study suggests that the data-driven ML model is a practicable technique and may act as an alternative way to perform mechanism analysis to some extent, and has immense potential to be applied in both problem research and decision-making for air pollution control.