摘要：This study integrates machine learning and particle‐resolved aerosol simulations to develop emulators that predict submicron aerosol mixing state indices from the Earth system model (ESM) simulations. The emulators predict aerosol mixing state using only quantities that are predicted by the ESM, including bulk aerosol species concentrations, which do not by themselves carry mixing state information. We used PartMC‐MOSAIC as the particle‐resolved model and NCAR's CESM as the ESM. We trained emulators for three different mixing state indices for submicron aerosol in terms of chemical species abundance ( χ a ), the mixing of optically absorbing and nonabsorbing species ( χ o ), and the mixing of hygroscopic and nonhygroscopic species ( χ h ). Our global mixing state maps show considerable spatial and seasonal variability unique to each mixing state index. Seasonal averages varied spatially between 13% and 94% for χ a , between 38% and 94% for χ o , and between 20% and 87% for χ h with global annual averages of 67%, 68%, and 56%, respectively. High values in one index can be consistent with low values in another index depending on the grouping of species and their relative abundance, meaning that each mixing state index captures different aspects of the population mixing state. Although a direct validation with observational data has not been possible yet, our results are consistent with mixing state index values derived from ambient observations. This work is a prototypical example of using machine learning emulators to add information to ESM simulations. Plain Language Abstract Earth system models (ESMs) simulations are computationally expensive, requiring highly simplified representations of aerosol mixing state, a property that describes how different aerosol chemical species are distributed among and within the aerosol particles. The assumption of whether aerosols are internally (multiple species within a particle), externally (one species per single particle), or intermediately mixed greatly influences the properties of aerosol particles and thereby the prediction of the impacts of air pollution on human health and climate change. We built simplified models using machine learning and highly detailed particle‐resolved simulations to infer submicron aerosol mixing state from meteorological parameters and pollution levels. These emulators enable us to estimate the degree of aerosol mixing state at a global scale using information that ESMs track. This study provides an example of the integration of detailed aerosol process modeling and a large‐scale ESM via machine learning.
