Deep Potential Molecular Dynamics: a scalable model with the accuracy of quantum mechanics
This provides a scalable and accurate simulation protocol for materials and molecular systems, addressing a bottleneck in computational chemistry and physics.
The authors tackled the problem of performing accurate molecular dynamics simulations by introducing the Deep Potential Molecular Dynamics (DeePMD) method, which uses a deep neural network trained on ab initio data to achieve results indistinguishable from quantum mechanics at a cost that scales linearly with system size.
We introduce a scheme for molecular simulations, the Deep Potential Molecular Dynamics (DeePMD) method, based on a many-body potential and interatomic forces generated by a carefully crafted deep neural network trained with ab initio data. The neural network model preserves all the natural symmetries in the problem. It is "first principle-based" in the sense that there are no ad hoc components aside from the network model. We show that the proposed scheme provides an efficient and accurate protocol in a variety of systems, including bulk materials and molecules. In all these cases, DeePMD gives results that are essentially indistinguishable from the original data, at a cost that scales linearly with system size.