GNN Surrogate Models for Accelerated Molecular Dynamics

This paper introduces a graph neural network (GNN) based surrogate model to accelerate molecular dynamics simulations. It bypasses the computationally expensive force calculations and numerical integration of traditional methods by directly predicting atomic displacements. The model's ability to maintain accuracy and preserve physical signatures, like radial distribution functions and mean squared displacement, is significant. This approach offers a promising and efficient alternative for atomistic simulations, particularly in metallic systems.