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

Molecular dynamics is a powerful simulation tool to explore materialproperties. Most of the realistic material systems are too large to besimulated with first-principles molecular dynamics. Classical moleculardynamics has lower computational cost but requires accurate force fields toachieve chemical accuracy. In this work, we develop a symmetry-adapted graphneural networks framework, named molecular dynamics graph neural networks(MDGNN), to construct force fields automatically for molecular dynamicssimulations for both molecules and crystals. This architecture consistentlypreserves the translation, rotation and permutation invariance in thesimulations. We propose a new feature engineering method including higher ordercontributions and show that MDGNN accurately reproduces the results of bothclassical and first-principles molecular dynamics. We also demonstrate thatforce fields constructed by the model has good transferability. Therefore,MDGNN provides an efficient and promising option for molecular dynamicssimulations of large scale systems with high accuracy.

Symmetry-adapted graph neural networks for constructing molecular dynamics force fields