Deep learning ferroelectric polarization distributions from STEM data via with and without atom finding

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. An...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Christopher T. Nelson, Ayana Ghosh, Mark Oxley, Xiaohang Zhang, Maxim Ziatdinov, Ichiro Takeuchi, Sergei V. Kalinin
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2021
Materias:	Materials of engineering and construction. Mechanics of materials TA401-492 Computer software QA76.75-76.765
Acceso en línea:	https://doaj.org/article/cc3e9a82689c4472ba644777e5a547c8
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:cc3e9a82689c4472ba644777e5a547c8
record_format	dspace
spelling	oai:doaj.org-article:cc3e9a82689c4472ba644777e5a547c82021-12-02T15:16:05ZDeep learning ferroelectric polarization distributions from STEM data via with and without atom finding10.1038/s41524-021-00613-62057-3960https://doaj.org/article/cc3e9a82689c4472ba644777e5a547c82021-09-01T00:00:00Zhttps://doi.org/10.1038/s41524-021-00613-6https://doaj.org/toc/2057-3960Abstract 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.Christopher T. NelsonAyana GhoshMark OxleyXiaohang ZhangMaxim ZiatdinovIchiro TakeuchiSergei V. KalininNature PortfolioarticleMaterials of engineering and construction. Mechanics of materialsTA401-492Computer softwareQA76.75-76.765ENnpj Computational Materials, Vol 7, Iss 1, Pp 1-11 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Materials of engineering and construction. Mechanics of materials TA401-492 Computer software QA76.75-76.765
spellingShingle	Materials of engineering and construction. Mechanics of materials TA401-492 Computer software QA76.75-76.765 Christopher T. Nelson Ayana Ghosh Mark Oxley Xiaohang Zhang Maxim Ziatdinov Ichiro Takeuchi Sergei V. Kalinin Deep learning ferroelectric polarization distributions from STEM data via with and without atom finding
description	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.
format	article
author	Christopher T. Nelson Ayana Ghosh Mark Oxley Xiaohang Zhang Maxim Ziatdinov Ichiro Takeuchi Sergei V. Kalinin
author_facet	Christopher T. Nelson Ayana Ghosh Mark Oxley Xiaohang Zhang Maxim Ziatdinov Ichiro Takeuchi Sergei V. Kalinin
author_sort	Christopher T. Nelson
title	Deep learning ferroelectric polarization distributions from STEM data via with and without atom finding
title_short	Deep learning ferroelectric polarization distributions from STEM data via with and without atom finding
title_full	Deep learning ferroelectric polarization distributions from STEM data via with and without atom finding
title_fullStr	Deep learning ferroelectric polarization distributions from STEM data via with and without atom finding
title_full_unstemmed	Deep learning ferroelectric polarization distributions from STEM data via with and without atom finding
title_sort	deep learning ferroelectric polarization distributions from stem data via with and without atom finding
publisher	Nature Portfolio
publishDate	2021
url	https://doaj.org/article/cc3e9a82689c4472ba644777e5a547c8
work_keys_str_mv	AT christophertnelson deeplearningferroelectricpolarizationdistributionsfromstemdataviawithandwithoutatomfinding AT ayanaghosh deeplearningferroelectricpolarizationdistributionsfromstemdataviawithandwithoutatomfinding AT markoxley deeplearningferroelectricpolarizationdistributionsfromstemdataviawithandwithoutatomfinding AT xiaohangzhang deeplearningferroelectricpolarizationdistributionsfromstemdataviawithandwithoutatomfinding AT maximziatdinov deeplearningferroelectricpolarizationdistributionsfromstemdataviawithandwithoutatomfinding AT ichirotakeuchi deeplearningferroelectricpolarizationdistributionsfromstemdataviawithandwithoutatomfinding AT sergeivkalinin deeplearningferroelectricpolarizationdistributionsfromstemdataviawithandwithoutatomfinding
_version_	1718387536571662336

Deep learning ferroelectric polarization distributions from STEM data via with and without atom finding

Ejemplares similares