Deep Learning with Reflection High-Energy Electron Diffraction Images to Predict Cation Ratio in Sr 2 x Ti 2(1– x ) O 3 Thin Films
Nano Letters · 09.04.2025 · 25 (14) · 5867-5874
DOI: 10.1021/acs.nanolett.5c00787 ↗Kurz gefasst
Fachartikel in der Zeitschrift Nano Letters, online erschienen am 31.03.2025. Verfasst von Sumner B Harris und 4 weiteren Autor:innen. Beteiligte Einrichtung: Center for Nanophase Materials Sciences, Oak Ridge National Laboratory, Oak Ridge, Tennessee 37831, United States. Die Arbeit wurde bisher 11-mal zitiert (Crossref) und nennt 38 Literaturangaben. Gefördert von: U.S. Department of Energy, National Science Foundation.
Abstract (Originalsprache)
Machine learning (ML) with in-situ diagnostics offers a transformative approach to accelerate, understand, and control thin film synthesis by uncovering relationships between synthesis conditions and material properties. In this study, we demonstrate the application of deep learning to predict the stoichiometry of Sr2xTi2(1-x)O3 thin films using reflection high-energy electron diffraction images acquired during pulsed laser deposition. A gated convolutional neural network trained for regression of the Sr atomic fraction achieved accurate predictions with a small dataset of 31 samples. Explainable AI techniques revealed a previously unknown correlation between diffraction streak features and cation stoichiometry in Sr2xTi2(1-x)O3 thin films. Our results demonstrate how ML can be used to transform a ubiquitous in-situ diagnostic tool, that is usually limited to qualitative assessments, into a quantitative surrogate measurement of continuously valued thin film properties. Such methods are critically needed to enable real-time control, autonomous workflows, and accelerate traditional synthesis approaches.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Center for Nanophase Materials Sciences, Oak Ridge National Laboratory, Oak Ridge, Tennessee 37831, United States.
- Department of Physics, Auburn University, 315 Roosevelt Concourse, Auburn, Alabama 36849, United States.
- Department of Materials Science and Engineering, University of Delaware, 201 DuPont Hall, Newark, Delaware 19716, United States.
ORCID-Profile: Sumner B Harris, Rama K Vasudevan, Ryan B Comes
Förderung
- U.S. Department of Energy
- National Science Foundation
Zitieren
APA
Harris, S. B., Gemperline, P. T., Rouleau, C. M., Vasudevan, R. K., & Comes, R. B. (2025). Deep Learning with Reflection High-Energy Electron Diffraction Images to Predict Cation Ratio in Sr 2 x Ti 2(1– x ) O 3 Thin Films. Nano Letters, 25(14), 5867-5874. https://doi.org/10.1021/acs.nanolett.5c00787
Vancouver
Harris SB, Gemperline PT, Rouleau CM, Vasudevan RK, Comes RB. Deep Learning with Reflection High-Energy Electron Diffraction Images to Predict Cation Ratio in Sr 2 x Ti 2(1– x ) O 3 Thin Films. Nano Letters. 2025;25(14):5867-5874. doi:10.1021/acs.nanolett.5c00787
BibTeX
@article{Harris2025,
author = {Harris, Sumner B and Gemperline, Patrick T and Rouleau, Christopher M and Vasudevan, Rama K and Comes, Ryan B},
title = {Deep Learning with Reflection High-Energy Electron Diffraction Images to Predict Cation Ratio in Sr 2 x Ti 2(1– x ) O 3 Thin Films},
journal = {Nano Letters},
year = {2025},
volume = {25},
number = {14},
pages = {5867--5874},
doi = {10.1021/acs.nanolett.5c00787}
}
EUVIMED