Kinetic models of Secondary Organic Aerosols (SOA) rely on accurate parametrizations of physical properties of semi-volatile organic species composing atmospheric particles. Notably, partitioning of SOA species between gas and particle phases is highly influenced by particle viscosity and phase state. SOA viscosity can be estimated from the glass transition temperature (Tg) of the constituting semi-volatiles which can be predicted from the elemental composition of single organic molecules. However, more accurate prediction methods that include information on molecular structure and functional groups presence are needed for modeling of complex SOA mixtures. Here, we introduce a new Tg prediction method powered by a machine learning (ML) model and by molecular embeddings, recently developed high-dimensional descriptors of chemical species. Molecular embeddings are vectorial molecular descriptors developed from word2vec based representations of chemical SMILES (i.e. mol2vec) which retain information on molecular substructures. We have trained state-of-the art ML models on the largest database of experimental Tg data of monomeric organic species and their corresponding molecular embeddings. Different algorithms have been explored for accuracy in predicting Tg. The final Tg prediction method is built on top of an Extreme Gradient Boosting (XGB) model and it largely outperforms previous Tg parametrizations. The new ML powered model has a mean absolute error of 19.0 K and a R2 of 0.97, it accounts for atoms connectivity within molecules and it can predict different Tg for compositional isomers. The new ML model can also reproduce experimental viscosity data and quantify the influence of number and location of functional groups within the molecule on organic compounds viscosity. This new ML powered Tg model can be exploited to predict viscosity in numerical models involving organic species, with future applications that go beyond aerosol chemistry and extend to modeling of organic molecules.

Predicting glass transition temperature of organic molecules via machine learning and molecular embeddings

ACS Fall 2021

The official archive and repository for all ACS Meetings & Expositions abstracts and select posters or presentations.