English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Techniques for training artificial neural networks (ANNs) and convolutionalneural networks (CNNs) using simulated dynamical electron diffraction patternsare described. The premise is based on the following facts. First, given asuitable crystal structure model and scattering potential, electron diffractionpatterns can be simulated accurately using dynamical diffraction theory.Secondly, using simulated diffraction patterns as input, ANNs can be trainedfor the determination of crystal structural properties, such as crystalorientation and local strain. Further, by applying the trained ANNs tofour-dimensional diffraction datasets (4D-DD) collected using the scanningelectron nanodiffraction (SEND) or 4D scanning transmission electron microscopy(4D-STEM) techniques, the crystal structural properties can be mapped at highspatial resolution. Here, we demonstrate the ANN-enabled possibilities for theanalysis of crystal orientation and strain at high precision and benchmark theperformance of ANNs and CNNs by comparing with previous methods. A factor ofthirty improvement in angular resolution at 0.009 degrees (0.16 mrad) fororientation mapping, sensitivity at 0.04% or less for strain mapping, andimprovements in computational performance are demonstrated.

Training artificial neural networks for precision orientation and strain mapping using 4D electron diffraction datasets