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/

Zendy Plus

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

Zendy Tools

Zendy Open

The phonon density-of-states (DOS) summarizes the lattice vibrational modessupported by a structure, and gives access to rich information about thematerial's stability, thermodynamic constants, and thermal transportcoefficients. Here, we present an atomistic line graph neural network (ALIGNN)model for the prediction of the phonon density of states and the derivedthermal and thermodynamic properties. The model is trained on a database ofover 14,000 phonon spectra included in the JARVIS-DFT (Joint AutomatedRepository for Various Integrated Simulations: Density Functional Theory)database. The model predictions are shown to capture the spectral features ofthe phonon density-of-states, effectively categorize dynamical stability, andlead to accurate predictions of DOS-derived thermal and thermodynamicproperties, including heat capacity $C_{\mathrm{V}}$, vibrational entropy$S_{\mathrm{vib}}$, and the isotopic phonon scattering rate$\tau^{-1}_{\mathrm{i}}$. The DOS-mediated ALIGNN model provides superiorpredictions when compared to a direct deep-learning prediction of thesematerial properties as well as predictions based on analytic simplifications ofthe phonon DOS, including the Debye or Born-von Karman models. Finally, theALIGNN model is used to predict the phonon spectra and properties for about40,000 additional materials listed in the JARVIS-DFT database, which arevalidated as far as possible against other open-sourced high-throughput DFTphonon databases.

Rapid Prediction of Phonon Structure and Properties using an Atomistic Line Graph Neural Network (ALIGNN)