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

First isolated in 2004, graphene monolayers display unique properties andpromising technological potential in next generation electronics,optoelectronics, and energy storage. The simple yet effective methodology,mechanical exfoliation followed by optical microscopy inspection, used forfabricating graphene has been exploited to discover many more two-dimensional(2D) atomic crystals which show distinct physical properties from their bulkcounterpart, opening the new era of materials research. However, manualinspection of optical images to identify 2D flakes has the clear drawback oflow-throughput and hence is impractical for any scale-up applications of 2Dsamples, albert their fascinating physical properties. Recent integration ofhigh-performance machine-learning, usually deep learning, techniques withoptical microscopy has accelerated flake identification. Despite theadvancement brought by deep learning algorithms, their high computationalcomplexities, large dataset requirements, and more importantly, opaquedecision-making processes limit their accessibilities. As an alternative, weinvestigate more transparent tree-based machine-learning algorithms withfeatures that mimic color contrast for the automated identification ofexfoliated 2D atomic crystals (e.g., MoSe2) under different optical settings.We compare the success and physical nature of the decisions of these tree-basedalgorithms to ResNet, a Convolutional Neural Network (CNN). We show thatdecision trees, gradient boosted decision trees, and random forests cansuccessfully classify optical images of thin materials with transparentdecisions that rely on physical image features and do not suffer from extremeoverfitting and large dataset requirements.

Physically informed machine-learning algorithms for the identification of two-dimensional atomic crystals