Coarse-Graining Auto-Encoders for Molecular Dynamics
This addresses the computational bottleneck in molecular dynamics simulations for materials science, enabling more efficient design of new compounds, though it is an incremental improvement over existing statistical mechanics methods.
The paper tackles the problem of coarse-graining in molecular dynamics by introducing Autograin, an auto-encoder-based framework that simultaneously learns the mapping from all-atom to reduced representations and parametrizes the coarse-grained Hamiltonian, achieving computational feasibility for larger systems and longer timesteps.
Molecular dynamics simulations provide theoretical insight into the microscopic behavior of materials in condensed phase and, as a predictive tool, enable computational design of new compounds. However, because of the large temporal and spatial scales involved in thermodynamic and kinetic phenomena in materials, atomistic simulations are often computationally unfeasible. Coarse-graining methods allow simulating larger systems, by reducing the dimensionality of the simulation, and propagating longer timesteps, by averaging out fast motions. Coarse-graining involves two coupled learning problems; defining the mapping from an all-atom to a reduced representation, and the parametrization of a Hamiltonian over coarse-grained coordinates. Multiple statistical mechanics approaches have addressed the latter, but the former is generally a hand-tuned process based on chemical intuition. Here we present Autograin, an optimization framework based on auto-encoders to learn both tasks simultaneously. Autograin is trained to learn the optimal mapping between all-atom and reduced representation, using the reconstruction loss to facilitate the learning of coarse-grained variables. In addition, a force-matching method is applied to variationally determine the coarse-grained potential energy function. This procedure is tested on a number of model systems including single-molecule and bulk-phase periodic simulations.