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

Molecular dynamics (MD) simulation, which is considered an important tool forstudying physical and chemical processes at the atomic scale, requires accuratecalculations of energies and forces. Although reliable energies and forces canbe obtained by electronic structure calculations such as those based on densityfunctional theory (DFT), this approach is computationally expensive. In thiswork, we propose a full-stack model using deep neural network (NN) to enhancethe calculation of force and energy, in which the NN is designed to extract theembedding feature of pairwise interactions of an atom and its neighbors, whichare aggregated to obtain its feature vector for predicting atomic force andpotential energy. By designing the features of the pairwise interactions, wecan control the performance of models and take into account the many-bodyeffects and other physics of the atomic interactions. Moreover, we demonstratedthat using the Coulomb matrix of the local structures in complement to thepairwise information, we can improve the prediction of force and energy forsilicon systems and the transferability of our models is confirmed to largersystems, with high accuracy.

Pairwise interactions for Potential energy surfaces and Atomic forces with Deep Neural network