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 Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Due to their ability to recognize complex patterns, neural networks can drivea paradigm shift in the analysis of materials science data. Here, we introduceARISE, a crystal-structure identification method based on Bayesian deeplearning. As a major step forward, ARISE is robust to structural noise and cantreat more than 100 crystal structures, a number that can be extended ondemand. While being trained on ideal structures only, ARISE correctlycharacterizes strongly perturbed single- and polycrystalline systems, from bothsynthetic and experimental resources. The probabilistic nature of theBayesian-deep-learning model allows to obtain principled uncertainty estimates,which are found to be correlated with crystalline order of metallicnanoparticles in electron tomography experiments. Applying unsupervisedlearning to the internal neural-network representations reveals grainboundaries and (unapparent) structural regions sharing easily interpretablegeometrical properties. This work enables the hitherto hindered analysis ofnoisy atomic structural data from computations or experiments.

Robust recognition and exploratory analysis of crystal structures via Bayesian deep learning