Deep Bayesian Local Crystallography

TL;DR

This paper introduces a Bayesian framework for analyzing atomically resolved microscopy images, enabling more accurate identification of local structures and symmetries in materials through deep learning methods.

Contribution

It develops a Bayesian approach to define and analyze symmetry in microscopy data, extending traditional concepts with deep learning techniques like variational autoencoders.

Findings

Bayesian symmetry definition improves structural analysis accuracy.

Deep learning models can effectively extract local symmetry information.

The approach enhances understanding of material structures at atomic resolution.

Abstract

The advent of high-resolution electron and scanning probe microscopy imaging has opened the floodgates for acquiring atomically resolved images of bulk materials, 2D materials, and surfaces. This plethora of data contains an immense volume of information on materials structures, structural distortions, and physical functionalities. Harnessing this knowledge regarding local physical phenomena necessitates the development of the mathematical frameworks for extraction of relevant information. However, the analysis of atomically resolved images is often based on the adaptation of concepts from macroscopic physics, notably translational and point group symmetries and symmetry lowering phenomena. Here, we explore the bottom-up definition of structural units and symmetry in atomically resolved data using a Bayesian framework. We demonstrate the need for a Bayesian definition of symmetry using a simple toy model and demonstrate how this definition can be extended to the experimental data using deep learning networks in a Bayesian setting, namely rotationally invariant variational autoencoders.