Deep Bayesian local crystallography

Sergei V. Kalinin, Mark P. Oxley, Mani Valleti, Junjie Zhang, Raphael P. Hermann, Hong Zheng, Wenrui Zhang, Gyula Eres, Rama K. Vasudevan, Maxim Ziatdinov

Research output: Contribution to journalArticlepeer-review

17 Scopus citations

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.

Original languageEnglish
Article number181
Journalnpj Computational Materials
Volume7
Issue number1
DOIs
StatePublished - Dec 2021

Funding

This effort (ML, STEM, film growth, sample growth) is based upon work supported by the U.S. Department of Energy (DOE), Office of Science, Basic Energy Sciences (BES), Materials Sciences and Engineering Division (S.V.K., S.V., G.E., W.Z., J.Z., H.Z., and R.P.H.) and was performed and partially supported (R.K.V. and M.Z.) at the Oak Ridge National Laboratory’s Center for Nanophase Materials Sciences (CNMS), a U.S. Department of Energy, Office of Science User Facility. Dr. Matthew Chisholm is gratefully acknowledged for the STEM data used in this work. Dr. Katharine Page is gratefully acknowledged for help in the data acquisition at NOMAD. A portion of this research used resources at the Spallation Neutron Source, a DOE Office of Science User Facility operated by the Oak Ridge National Laboratory. The authors are deeply grateful to Dr. Karren More for careful reading and correcting the manuscript.

Fingerprint

Dive into the research topics of 'Deep Bayesian local crystallography'. Together they form a unique fingerprint.

Cite this