Learning Large-Time-Step Molecular Dynamics with Graph Neural Networks
arXiv:2111.15176
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.
arXiv comment7 pages, 2 figures. NeurIPS 2021 AI for Science Workshop
References in corpus (6)
- Deep Potential Molecular Dynamics: a scalable model with the accuracy of quantum mechanics
- Searching for Activation Functions
- Deep Graph Library: A Graph-Centric, Highly-Performant Package for Graph Neural Networks
- E(n) Equivariant Graph Neural Networks
- Deep Lagrangian Networks: Using Physics as Model Prior for Deep Learning
- Data-driven Prediction of General Hamiltonian Dynamics via Learning Exactly-Symplectic Maps