Deep learning polarization distributions in ferroelectrics from STEM data: with and without atom finding

TL;DR

This paper investigates the use of deep convolutional neural networks to directly map polarization in ferroelectric materials from STEM images, bypassing traditional atomic position detection, and evaluates its effectiveness and limitations.

Contribution

It introduces a deep learning approach for polarization mapping directly from STEM images, reducing reliance on atomic position detection and assessing transferability across compositions.

Findings

DCNN can effectively analyze STEM images for polarization mapping

The choice of descriptors impacts the analysis accuracy

Network transferability varies with composition

Abstract

Over the last decade, scanning transmission electron microscopy (STEM) has emerged as a powerful tool for probing atomic structures of complex materials with picometer precision, opening the pathway toward exploring ferroelectric, ferroelastic, and chemical phenomena on the atomic-scale. Analyses to date extracting a polarization signal from lattice coupled distortions in STEM imaging rely on discovery of atomic positions from intensity maxima/minima and subsequent calculation of polarization and other order parameter fields from the atomic displacements. Here, we explore the feasibility of polarization mapping directly from the analysis of STEM images using deep convolutional neural networks (DCNNs). In this approach, the DCNN is trained on the labeled part of the image (i.e., for human labelling), and the trained network is subsequently applied to other images. We explore the effects of the choice of the descriptors (centered on atomic columns and grid-based), the effects of observational bias, and whether the network trained on one composition can be applied to a different one. This analysis demonstrates the tremendous potential of the DCNN for the analysis of high-resolution STEM imaging and spectral data and highlights the associated limitations.