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 predicts the trajectory of atoms bysolving Newton's equation of motion with a numeric integrator. Due to physicalconstraints, the time step of the integrator need to be small to maintainsufficient precision. This limits the efficiency of simulation. To this end, weintroduce a graph neural network (GNN) based model, MDNet, to predict theevolution of coordinates and momentum with large time steps. In addition, MDNetcan easily scale to a larger system, due to its linear complexity with respectto the system size. We demonstrate the performance of MDNet on a 4000-atomsystem with large time steps, and show that MDNet can predict good equilibriumand transport properties, well aligned with standard MD simulations.

Learning Large-Time-Step Molecular Dynamics with Graph Neural Networks