DeePCG: constructing coarse-grained models via deep neural networks

TL;DR

DeePCG introduces a neural network-based framework for constructing accurate, many-body coarse-grained potential models directly from atomistic data, enabling faster sampling while preserving system symmetries.

Contribution

The paper presents a novel neural network approach for creating coarse-grained potentials without ad hoc approximations, improving accuracy and efficiency.

Findings

The DeePCG model accurately reproduces many-body correlations in liquid water.

The coarse-grained model significantly speeds up sampling compared to atomistic simulations.

The approach preserves natural symmetries of the system.

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 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 found 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.