Exploring Physics of Ferroelectric Domain Walls in Real Time: Deep Learning Enabled Scanning Probe Microscopy

TL;DR

This paper introduces a deep learning framework integrated with scanning probe microscopy for real-time analysis and visualization of ferroelectric domain walls, enabling dynamic studies of their behavior in ferroelectric materials.

Contribution

It presents a novel real-time deep convolutional neural network approach for semantic segmentation of domain walls in SPM data, addressing out-of-distribution effects and demonstrating dynamic domain wall analysis.

Findings

Real-time segmentation of domain walls achieved in SPM data.

Identification of dynamic ferroelastic domain wall behavior in PTO and PZT films.

Framework for real-time microscale data analysis established.

Abstract

The functionality of ferroelastic domain walls in ferroelectric materials is explored in real-time via the in-situ implementation of computer vision algorithms in scanning probe microscopy (SPM) experiment. The robust deep convolutional neural network (DCNN) is implemented based on a deep residual learning framework (Res) and holistically-nested edge detection (Hed), and ensembled to minimize the out-of-distribution drift effects. The DCNN is implemented for real-time operations on SPM, converting the data stream into the semantically segmented image of domain walls and the corresponding uncertainty. We further demonstrate the pre-selected experimental workflows on thus discovered domain walls, and report alternating high- and low- polarization dynamic (out-of-plane) ferroelastic domain walls in a (PbTiO3) PTO thin film and high polarization dynamic (out-of-plane) at short ferroelastic walls (compared with long ferroelastic walls) in a lead zirconate titanate (PZT) thin film. This work establishes the framework for real-time DCNN analysis of data streams in scanning probe and other microscopies and highlights the role of out-of-distribution effects and strategies to ameliorate them in real time analytics.