Abstract
Secondary organic aerosols (SOA) are formed from oxidation of hundreds of volatile organic compounds (VOCs) emitted from anthropogenic and natural sources. Accurate predictions of this chemistry are key for air quality and climate studies due to the large contribution of organic aerosols to submicron aerosol mass. Currently, only explicit models, such as the Generator for Explicit Chemistry and Kinetics of Organics in the Atmosphere (GECKO‐A), can fully represent the chemical processing of thousands of organic species. However, their extreme computational cost prohibits their use in current chemistry‐climate models, which rely on simplified empirical parameterizations to predict SOA concentrations. This study demonstrates that machine learning can accurately emulate SOA formation from an explicit chemistry model with an approximate error of 2%–8%, up to five days for several precursors and for potentially up to one month for recurrent neural network models, and with 100 to 100,000 times speedup over GECKO‐A, making it computationally useable in a chemistry‐climate model. We generated the training data using thousands of GECKO‐A box simulations sampled from a broad range of initial environmental conditions, and focused on three representative SOA precursors: the oxidation by OH of two anthropogenic (toluene, dodecane), and the oxidation by O3 of one biogenic VOC (α‐pinene). We compare several neural models and quantify their underlying uncertainty and robustness. These are promising results, suggesting that neural network models could be applied to predict SOA in chemistry‐climate models, limited however to the range of environmental conditions that were considered in the training datasets. Plain Language Summary Detailed and accurate representation of organic aerosol chemistry is needed to predict the effect of atmospheric aerosols formed from natural and anthropogenic sources on both human health and climate. Ideally, these complex representations of chemistry would be directly included within state‐of‐the‐art weather and climate models to get a fully coupled system with meteorological and climatological feedback all over the globe. However, we are many years away from having the computational power needed to run such fully coupled large‐scale simulations due to the complexity of organic chemistry, which involves hundreds of thousands of organic gaseous and particle species and chemical reactions. As a potential solution, we test an approach that uses a neural network to mimic the solution of an explicit representation of organic chemistry which would be computationally feasible to link with current air quality and climate models. Key Points Incorporation of explicit organic chemistry into 3D chemistry‐simulations requires emulation We developed two types of neural network emulators for the Generator for Explicit Chemistry and Kinetics of Organics in the Atmosphere chemistry model The emulators produced accurate and stable simulations for three precursor species