Deep learning of interface structures from the 4D STEM data: cation intermixing vs. roughening

TL;DR

This paper develops a deep learning approach using convolutional neural networks trained on simulated 4D STEM data to accurately characterize interface structures in complex oxides, distinguishing roughness and chemical diffusion.

Contribution

It introduces a novel deep learning method trained on simulated datasets to analyze interface structures in STEM data, enabling high-accuracy predictions of interface properties.

Findings

Achieved over 95% accuracy in identifying rough versus diffuse interfaces.

Successfully determined buried step positions with 85% accuracy.

Demonstrated the general applicability of the method to inverse imaging problems.

Abstract

Interface structures in complex oxides remain one of the active areas of condensed matter physics research, largely enabled by recent advances in scanning transmission electron microscopy (STEM). Yet the nature of the STEM contrast in which the structure is projected along the given direction precludes separation of possible structural models. Here, we utilize deep convolutional neural networks (DCNN) trained on simulated 4D scanning transmission electron microscopy (STEM) datasets to predict structural descriptors of interfaces. We focus on the widely studied interface between LaAlO3 and SrTiO3, using dynamical diffraction theory and leveraging high performance computing to simulate thousands of possible 4D STEM datasets to train the DCNN to learn properties of the underlying structures on which the simulations are based. We validate the DCNN on simulated data and show that it is possible (with >95% accuracy) to identify a physically rough from a chemically diffuse interface and achieve 85% accuracy in determination of buried step positions within the interface. The method shown here is general and can be applied for any inverse imaging problem where forward models are present.