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

We present a novel deep learning (DL) approach to produce highly accuratepredictions of macroscopic physical properties of solid solution binary alloysand magnetic systems. The major idea is to make use of the correlations betweendifferent physical properties in alloy systems to improve the predictionaccuracy of neural network (NN) models. We use multitasking NN models tosimultaneously predict the total energy, charge density and magnetic moment.These physical properties mutually serve as constraints during the training ofthe multitasking NN, resulting in more reliable DL models because multiplephysics properties are correctly learned by a single model. Two binary alloys,copper-gold (CuAu) and iron-platinum (FePt), were studied. Our results showthat once the multitasking NN's are trained, they can estimate the materialproperties for a specific configuration hundreds of times faster thanfirst-principles density functional theory calculations while retainingcomparable accuracy. We used a simple measure based on the root-mean-squarederrors (RMSE) to quantify the quality of the NN models, and found that theinclusion of charge density and magnetic moment as physical constraints leadsto more stable models that exhibit improved accuracy and reduced uncertaintyfor the energy predictions.

Fast and stable deep-learning predictions of material properties for solid solution alloys