Knowledge-guided machine learning reveals pivotal drivers for gas-to-particle conversion of atmospheric nitrate

Particulate nitrate, a key component of fine particles, forms through the intricate gas-to-particle con-version process. This process is regulated by the gas-to-particle conversion coefficient of nitrate (epsilon(NO3 =)). The mechanism between epsilon(NO3 =) and its drivers is highly complex and nonlinear, and can be charac-terized by machine learning methods. However, conventional machine learning often yields results that lack clear physical meaning and may even contradict established physical/chemical mechanisms due to the influence of ambient factors. It urgently needs an alternative approach that possesses transparent physical interpretations and provides deeper insights into the impact of epsilon(NO3 =). Here we introduce a supervised machine learning approachdthe multilevel nested random forest guided by theory ap-proaches. Our approach robustly identifies NH4 thorn , SO42 =, and temperature as pivotal drivers for epsilon(NO3 =). Notably, substantial disparities exist between the outcomes of traditional random forest analysis and the anticipated actual results. Furthermore, our approach underscores the significance of NH4 thorn during both daytime (30%) and nighttime (40%) periods, while appropriately downplaying the influence of some less relevant drivers in comparison to conventional random forest analysis. This research underscores the transformative potential of integrating domain knowledge with machine learning in atmospheric studies. (c) 2023 The Authors. Published by Elsevier B.V. on behalf of Chinese Society for Environmental Sciences, Harbin Institute of Technology, Chinese Research Academy of Environmental Sciences. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).