In situ scanning transmission electron microscopy enables observation of the domain dynamics in ferroelectric materials as a function of externally applied bias and temperature. The resultant data sets contain a wealth of information on polarization switching and phase transition mechanisms. However, identification of these mechanisms from observational data sets has remained a problem due to a large variety of possible configurations, many of which are degenerate. Here, we introduce an approach based on rotationally invariant variational autoencoder (VAE), which enables learning a latent space representation of the data with multiple real-space rotationally equivalent variants mapped to the same latent space descriptors. By varying the size of training sub-images in the VAE, we tune the degree of complexity in the structural descriptors from simple domain wall detection to the identification of switching pathways. This yields a powerful tool for the exploration of the dynamic data in mesoscopic electron, scanning probe, optical, and chemical imaging. Moreover, this work adds to the growing body of knowledge of incorporating physical constraints into the machine and deep-learning methods to improve learned descriptors of physical phenomena.
Comment: Minor updates (affiliations, abstract, data statement)