A GRU neural network trained on ring-statistics time series from TIP4P/2005 water simulations predicts thermodynamic response functions, with mixed extrapolation accuracy to unseen isobars.
Learning Large-Time-Step Molecular Dynamics with Graph Neural Networks
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
Molecular dynamics (MD) simulation predicts the trajectory of atoms by solving Newton's equation of motion with a numeric integrator. Due to physical constraints, the time step of the integrator need to be small to maintain sufficient precision. This limits the efficiency of simulation. To this end, we introduce a graph neural network (GNN) based model, MDNet, to predict the evolution of coordinates and momentum with large time steps. In addition, MDNet can easily scale to a larger system, due to its linear complexity with respect to the system size. We demonstrate the performance of MDNet on a 4000-atom system with large time steps, and show that MDNet can predict good equilibrium and transport properties, well aligned with standard MD simulations.
citation-role summary
background 1
citation-polarity summary
fields
physics.chem-ph 1years
2025 1verdicts
REJECT 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Predicting Thermodynamics of Liquid Water from Time Series Analysis
A GRU neural network trained on ring-statistics time series from TIP4P/2005 water simulations predicts thermodynamic response functions, with mixed extrapolation accuracy to unseen isobars.