Identification of the glass transition temperature Tg via selective dynamical slowing in bulk polymer melts using unsupervised machine learning.
Determining the glass transition temperature Tg in materials science in general and for amorphous polymer systems in particular is a delicate matter due to the uncertainty in the definition of Tg and the complexity of the glass transition phenomenon itself. Machine learning (ML) provides powerful approaches for analyzing complex, high-dimensional data to reveal hidden patterns. Recently, we have applied an unsupervised ML technique to identify Tg of a polymer melt of weakly semiflexible bead-spring chains using the time evolvement of pairwise internal distances between monomers along chains, as input features. Here, we investigate the change of individual internal chain relaxation as the polymer melt transforms from the liquid to glassy state. The average overall relaxation remains unchanged and displays the usual temperature dependence. However, for some individual pair distances, scattered throughout the sample, relaxation is significantly delayed, which serves as a robust indicator of approaching the glass transition. Moreover, these changes and the first principle components are highly correlated. This is an evidence that the ML technique indeed captures a significant indicator of the approach of the glass transition. Typical experiments, which average over the whole sample, cannot identify such features.