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

Developing methods to understand and control defect formation innanomaterials offers a promising route for materials discovery. Monolayer MX2phases represent a particularly compelling case for defect engineering ofnanomaterials due to the large variability in their physical properties asdifferent defects are introduced into their structure. However, effectiveidentification and quantification of defects remains a challenge even ashigh-throughput scanning tunneling electron microscopy (STEM) methods improve.This study highlights the benefits of employing first principles calculationsto produce digital twins for training deep learning segmentation models fordefect identification in monolayer MX2 phases. Around 600 defect structureswere obtained using density functional theory calculations, with each monolayerMX2 structure being subjected to multislice simulations for the purpose ofgenerating the digital twins. Several deep learning segmentation architectureswere trained on this dataset, and their performances evaluated under a varietyof conditions such as recognizing defects in the presence of unidentifiedimpurities, beam damage, grain boundaries, and with reduced image quality fromlow electron doses. This digital twin approach allows benchmarking differentdeep learning architectures on a theory dataset, which enables the study ofdefect classification under a broad array of finely controlled conditions. Itthus opens the door to resolving the underpinning physical reasons for modelshortcomings, and potentially chart paths forward for automated discovery ofmaterials defect phases in experiments.

Bridging Theory with Experiment: Digital Twins and Deep Learning Segmentation of Defects in Monolayer MX2 Phases