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

Carbon fiber and graphene-based nanostructures such as carbon nanotubes(CNTs) and defective structures have extraordinary potential as strong andlightweight materials. A longstanding bottleneck has been lack of understandingand implementation of atomic-scale engineering to harness the theoreticallimits of modulus and tensile strength, of which only a fraction is routinelyreached today. Here we demonstrate accurate and fast predictions of mechanicalproperties for CNTs and arbitrary 3D graphitic assemblies based on a trainingset of over 1000 stress-strain curves from cutting-edge reactive MD simulationand machine learning (ML). Several ML methods are compared and show that ournewly proposed hierarchically structured graph neural networks with spatialinformation (HS-GNNs) achieve predictions in modulus and strength for any 3Dnanostructure with only 5-10% error across a wide range of possible values. Thereliability is sufficient for practical applications and a great improvementover off-the shelf ML methods with up to 50% deviation, as well as over earliermodels for specific chemistry with 20% deviation. The algorithms allow morethan 10 times faster mechanical property predictions than traditional moleculardynamics simulations, the identification of the role of defects and random 3Dmorphology, and high-throughput screening of 3D structures for enhancedmechanical properties. The algorithms can be scaled to morphologies up to 100nm in size, expanded for chemically similar compounds, and trained to predict abroader range of properties.

Prediction of Carbon Nanostructure Mechanical Properties and Role of Defects Using Machine Learning