Symmetry-adapted graph neural networks for constructing molecular dynamics force fields
This work provides an efficient and accurate method for molecular dynamics simulations of large-scale systems, which is crucial for materials science and chemistry.
The authors developed Molecular Dynamics Graph Neural Networks (MDGNN), a symmetry-adapted graph neural network framework to automatically construct force fields for molecular dynamics simulations of molecules and crystals. This architecture accurately reproduces results from both classical and first-principles molecular dynamics, and the constructed force fields exhibit good transferability.
Molecular dynamics is a powerful simulation tool to explore material properties. Most of the realistic material systems are too large to be simulated with first-principles molecular dynamics. Classical molecular dynamics has lower computational cost but requires accurate force fields to achieve chemical accuracy. In this work, we develop a symmetry-adapted graph neural networks framework, named molecular dynamics graph neural networks (MDGNN), to construct force fields automatically for molecular dynamics simulations for both molecules and crystals. This architecture consistently preserves the translation, rotation and permutation invariance in the simulations. We propose a new feature engineering method including higher order contributions and show that MDGNN accurately reproduces the results of both classical and first-principles molecular dynamics. We also demonstrate that force fields constructed by the model has good transferability. Therefore, MDGNN provides an efficient and promising option for molecular dynamics simulations of large scale systems with high accuracy.