Machine-Learning-Based Prediction of the Glass Transition Temperature of Organic Compounds Using Experimental Data

Abstract

Knowledge of the glass transition temperature of molecular compounds that occur in atmospheric aerosol particles is important for estimating their viscosity, as it directly influences the kinetics of chemical reactions and particle phase state. While there is a great diversity of organic compounds present in aerosol particles, for only a minor fraction of them experimental glass transition temperatures are known. Therefore, we have developed a machine learning model designed to predict the glass transition temperature of organic molecular compounds based on molecule-derived input variables. The extremely randomized trees (extra trees) procedure was chosen for this purpose. Two approaches using different sets of input variables were followed. The first one uses the number of selected functional groups present in the compound, while the second one generates descriptors from a SMILES (Simplified Molecular Input Line Entry System) string. Organic compounds containing carbon, hydrogen, oxygen, nitrogen, and halogen atoms are included. For improved results, both approaches can be combined with the melting temperature of the compound as an additional input variable. The results show that the predictions of both approaches show a similar mean absolute error of about 12–13 K, with the SMILES-based predictions performing slightly better. In general, the model shows good predictive power considering the diversity of the experimental input data. Furthermore, we also show that its performance exceeds that of previous parameterizations developed for this purpose and also performs better than existing machine learning models. In order to provide user-friendly versions of the model for applications, we have developed a web site where the model can be run by interested scientists via a web-based interface without prior technical knowledge. We also provide Python code of the model. Additionally, all experimental input data are provided in form of the Bielefeld Molecular Organic Glasses (BIMOG) database. We believe that this model is a powerful tool for many applications in atmospheric aerosol science and material science.

Artificial Intelligence for Conjugated Polymers

“…It reflects the point at which the molecular chains in the polymer start to undergo significant movement, and it is typically quantified through differential scanning calorimetry (DSC, Figure 6a). 72 A higher T g often indicates enhanced thermal stability and rigidity of conjugated polymers, which can be advantageous in applications requiring dimensional stability or resistance to high temperatures. Conversely, a lower T g facilitates heightened molecular dynamics and flexibility, imparting a favorable softness and stretchability to the material.…”

“…The glass transition temperature ( T g ) is a key indicator of a conjugated polymer’s thermal behavior. , T g is the temperature at which the conjugated polymer transitions from a brittle, vitrified state to a more flexible, rubbery state. It reflects the point at which the molecular chains in the polymer start to undergo significant movement, and it is typically quantified through differential scanning calorimetry (DSC, Figure a) . A higher T g often indicates enhanced thermal stability and rigidity of conjugated polymers, which can be advantageous in applications requiring dimensional stability or resistance to high temperatures.…”

“…ML algorithms for conjugated polymers T g values prediction. (a) a DSC curve for glass transition temperature . Reproduced with permission from ref .…”

“…(a) a DSC curve for glass transition temperature . Reproduced with permission from ref . Copyright 2023 American Chemical Society.…”

Optimizing the performance of phase-change azobenzene: from trial and error to machine learning

“…In addition to simulation calculations, some machine learning based phase prediction methods have been proposed. Armeli et al 175 built a dataset by collecting experimental data on a large number of organic compounds, including information on molecular structure, physical properties and glass transition temperature ( T g ). Two distinct input modes were devised, wherein the molecular information is encoded through either the type and quantity of functional groups or derived from a SMILES string.…”