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

Inverse design of materials with desired properties is currently laboriousand heavily relies on intuition of researchers through a trial-and-errorprocess. The massive combinational spaces due to the constituent elements andtheir structural configurations are too overwhelming to be all searched even byhigh-throughput computations. Herein, we demonstrated a novel regressionalgenerative adversarial network (RGAN) for inverse design of representativetwo-dimensional materials, graphene and boron-nitride (BN) hybrids. Asignificant novelty of the proposed RGAN is that it combines the supervised andregressional convolutional neural network (CNN) with the traditionalunsupervised GAN, thus overcoming the common technical barrier in thetraditional GANs, which cannot generate data associated with given continuousquantitative labels. The proposed RGAN enables to autonomously generategraphene/BN hybrids with any given bandgaps. Moreover, the generated structuresexhibit high fidelity, yielding bandgaps within ~ 10% MAEF of the desiredbandgaps as cross-validated by density functional theory (DFT) calculations.Further analysis by principle component analysis (PCA) and modified locallylinear embedding (MLLE) methods on the latent features encoded by the regressorreveals that the generator has successfully generated structures that followedthe statistical distribution of the real structures. It implies the possibilityof the RGAN in recognizing physical rules hidden in the high-dimensional data.This new inverse design methodology would speed up the discovery anddevelopment of other 2D materials and beyond.

Inverse Structural Design of Graphene/Boron Nitride Hybrids by Regressional GAN