Skip to content

Read-only version: For security reasons, the Research Information System (FIS) has been temporarily replaced by this read-only version. All public content and full texts remain available; login, editing, submission and statistics are not available. Questions: fis@uni-bamberg.de

Home › Publications › Fast approximate STEM image simulations from a machine learning model

Publication

Fast approximate STEM image simulations from a machine learning model

Combs, Aidan H.; Maldonis, Jason J.; Feng, Jie; u. a. (2019): Fast approximate STEM image simulations from a machine learning model, in: Advanced Structural and Chemical Imaging, Cham: Springer Science and Business Media LLC, Jg. 5, Nr. 1, 2, S. 1–10, doi: 10.1186/s40679-019-0064-2.

Details

Faculty/Chair
Faculty/Professorship
Author
Combs, Aidan H.
Maldonis, Jason J.
Feng, Jie
Xu, Zhongnan
Voyles, Paul M.
Morgan, Dane
Title of the Journal
Advanced Structural and Chemical Imaging
ISSN
2198-0926
Publisher Information
Springer Science and Business Media LLC : Cham
Year of publication
2019
Volume
5
Issue
1, 2
Language
English
DOI
Abstract

Accurate quantum mechanical scanning transmission electron microscopy image simulation methods such as the multislice method require computation times that are too large to use in applications in high-resolution materials imaging that require very large numbers of simulated images. However, higher-speed simulation methods based on linear imaging models, such as the convolution method, are often not accurate enough for use in these applications. We present a method that generates an image from the convolution of an object function and the probe intensity, and then uses a multivariate polynomial fit to a dataset of corresponding multislice and convolution images to correct it. We develop and validate this method using simulated images of Pt and Pt–Mo nanoparticles and find that for these systems, once the polynomial is fit, the method runs about six orders of magnitude faster than parallelized CPU implementations of the multislice method while achieving a 1 − R2 error of 0.010–0.015 and root-mean-square error/standard deviation of dataset being predicted of about 0.1 when compared to full multislice simulations.

GND Keywords
Raster-Transmissions-Elektronenmikroskopie
Faltung <Mathematik>
MSCT
Lineare Regression
Keywords
Scanning transmission electron microscopy
Convolution
Frozen phonon multislice simulation
High-throughput
Linear regression
DDC Classification
004 Computer science
RVK Classification
ST 330
Peer Reviewed
yes
International Distribution
yes
Open Access Journal
yes
Type
Article
URI
Activation date
2024-08-13

Permalink: https://fis.uni-bamberg.de/handle/uniba/97250 · Data as JSON · Cite: BibTeX · RIS

Data as of: 2026-11-16

Restricted read-only access: login, editing and submission are temporarily disabled.