Decoding the mechanisms of phase transitions from in situ microscopy observations

TL;DR

This paper introduces a machine learning-based method to analyze in situ microscopy data, revealing phase transition mechanisms in BaTiO3 by examining domain morphology changes during temperature variations.

Contribution

It presents a novel workflow combining statistical analysis and dimensionality reduction to interpret dynamic microscopy data for phase transition studies.

Findings

Successfully visualized transformation pathways during phase transitions.

Demonstrated applicability to mesoscopic STEM data and potential for other imaging modalities.

Provides a general approach extendable to higher-dimensional material analysis.

Abstract

Temperature-induced phase transition in BaTiO3 has been explored using the machine learning analysis of domain morphologies visualized via variable-temperature scanning transmission electron microscopy (STEM) imaging data. This approach is based on the multivariate statistical analysis of the time or temperature dependence of the statistical descriptors of the system, derived in turn from the categorical classification of observed domain structures or projection on the continuous parameter space of the feature extraction-dimensionality reduction transform. The proposed workflow offers a powerful tool for the exploration of the dynamic data based on the statistics of image representation as a function of the external control variable to visualize the transformation pathways during phase transitions and chemical reactions. This can include the mesoscopic STEM data as demonstrated here, but also optical, chemical imaging, etc. data. It can further be extended to the higher dimensional spaces, for example, analysis of the combinatorial libraries of materials compositions.