Transfer learning-driven artificial intelligence model for glass transition temperature estimation of molecular glass formers mixtures

Predicting binary mixtures' glass transition temperature ( T g ) is crucial in various fields, particularly for industrial materials affected by this property during production processes and in service-life. On the other hand, from the fundamental point of view, this predictive capability is relevant for understanding the chemical interactions between the two components and how this affects the T g of the mixture. In this sense, some models provide different approaches for describing the T g of the mixture. Among them, the Gordon -Taylor approach has been widely used since it only relies on the relationship between the T g of the pure components, their weight fraction, and only one fitting parameter. Although simple, this approach still requires measurements of T g of the pure components and at least some intermediated composition for the fitting procedure. In a previous work, our research has focused on neural networks methods for predicting T g values directly from the chemical structure of monomers and molecules, but the scarcity of experimental data for binary mixtures limits the application of a similar approach. To address this problem, we propose to use in this work a transfer learning method that relays on the previous acquired knowledge of the chemical structure - T g relationship, for the prediction of the T g of the binary mixtures. Therefore, pure component characteristics are derived from chemical fingerprints originated in a pre-trained network, and enables a training process focused on their behavior within the mixtures. This approach successfully estimated K with very low deviations, even allowing for the exploration of the embedded chemical structure's relation to previously unknown mixtures.