DeePCG: Constructing coarse-grained models via deep neural networks
Abstract
We introduce a general framework for constructing coarse-grained potential models without ad hoc approximations such as limiting the potential to two- and/or three-body contributions. The scheme, called the Deep Coarse-Grained Potential (abbreviated DeePCG), exploits a carefully crafted neural network to construct a many-body coarse-grained potential. The network is trained with full atomistic data in a way that preserves the natural symmetries of the system. The resulting model is very accurate and can be used to sample the configurations of the coarse-grained variables in a much faster way than with the original atomistic model. As an application, we consider liquid water and use the oxygen coordinates as the coarse-grained variables, starting from a full atomistic simulation of this system at the ab initio molecular dynamics level. We find that the two-body, three-body, and higher-order oxygen correlation functions produced by the coarse-grained and full atomistic models agree very well with each other, illustrating the effectiveness of the DeePCG model on a rather challenging task.
Document Details
- Document Type
- Pub Defense Publication
- Publication Date
- Jul 16, 2018
- Source ID
- 10.1063/1.5027645
Entities
People
- Han Wang
- Jiequn Han
- Linfeng Zhang
- Roberto Car
- Weinan E
Organizations
- Beijing Institute of Big Data Research
- Institute of Applied Physics and Computational Mathematics
- Office of Naval Research
- Princeton University
- United States Department of Energy