Deep Learning of Atomically Resolved Scanning Transmission Electron Microscopy Images: Chemical Identification and Tracking Local Transformations

TL;DR

This paper presents a deep learning method for analyzing atomically resolved microscopy images, enabling chemical identification and tracking of local atomic transformations without extensive prior knowledge.

Contribution

The authors develop a weakly-supervised deep neural network approach to identify atomic species and defects in microscopy images, including unseen defect types and dynamic transformations.

Findings

Successfully identified atomic species and defects in microscopy images.

Tracked complex atomic and defect transformations over time.

Demonstrated scalability and human-like reasoning in data analysis.

Abstract

Recent advances in scanning transmission electron and scanning probe microscopies have opened exciting opportunities in probing the materials structural parameters and various functional properties in real space with angstrom-level precision. This progress has been accompanied by an exponential increase in the size and quality of datasets produced by microscopic and spectroscopic experimental techniques. These developments necessitate adequate methods for extracting relevant physical and chemical information from the large datasets, for which a priori information on the structures of various atomic configurations and lattice defects is limited or absent. Here we demonstrate an application of deep neural networks to extract information from atomically resolved images including location of the atomic species and type of defects. We develop a 'weakly-supervised' approach that uses information on the coordinates of all atomic species in the image, extracted via a deep neural network, to identify a rich variety of defects that are not part of an initial training set. We further apply our approach to interpret complex atomic and defect transformation, including switching between different coordination of silicon dopants in graphene as a function of time, formation of peculiar silicon dimer with mixed 3-fold and 4-fold coordination, and the motion of molecular 'rotor'. This deep learning based approach resembles logic of a human operator, but can be scaled leading to significant shift in the way of extracting and analyzing information from raw experimental data.