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

Autonomous materials discovery with desired properties is one of the ultimategoals for materials science, and the current studies have been focusing mostlyon high-throughput screening based on density functional theory calculationsand forward modelling of physical properties using machine learning. Applyingthe deep learning techniques, we have developed a generative model which canpredict distinct stable crystal structures by optimizing the formation energyin the latent space. It is demonstrated that the optimization of physicalproperties can be integrated into the generative model as on-top screening orbackwards propagator, both with their own advantages. Applying the generativemodels on the binary Bi-Se system reveals that distinct crystal structures canbe obtained covering the whole composition range, and the phases on the convexhull can be reproduced after the generated structures are fully relaxed to theequilibrium. The method can be extended to multicomponent systems formulti-objective optimization, which paves the way to achieve the inverse designof materials with optimal properties.

Constrained crystals deep convolutional generative adversarial network for the inverse design of crystal structures