Identification of response regulation governing ozone formation based on influential factors using a random forest approach.

The pursuit of enhanced scientific, refined, and precise ozone and air quality control continues to pose significant challenges. Using data visualization techniques and random forest (RF) algorithms, the temporal distribution of atmospheric pollutants and the interrelationship between O concentration and its influential factors were investigated with one-year monitoring data in Deqing county in 2021. The local atmospheric conditions predominantly belonged to NOx-sensitive and transition zone. Extremely high O concentration were primarily observed when temperatures (T) exceeded 30 °C, with relative humidity (RH) ranging between 30 and 60 %. NO, RH and T were identified as the top 3 important factors, and O concentration have stronger linearly relationship to RH and T, while stronger nonlinearly relationship to NO. By employing an optimized RF model, controlling consistent mild and high reaction atmospheric conditions, the O concentration response to the change of individual influencing factors was acquired. The O concentration increased and then decreased in response to the increasing NO concentration, displaying a characteristic inflection point at 10 μg m. More reactive radicals produced at higher VOCs concentration and continuing NO cycle at lower NO concentration, resulting in the acceleration in the direction of producing more O. Therefore, the significant different O response to variation of VOCs and NO concentration between mild and high reaction atmospheric conditions, as well as the existing of oxidant elevation should be considered in local air quality control. This study demonstrates the efficacy of ML methods in simulating nonlinear response of O, supports the understanding of local O formation and quick guidance for precise local O pollution control and the related strategies.