Adversarial reverse mapping of equilibrated condensed-phase molecular structures
A tight and consistent link between resolutions is crucial to further expand the impact of multiscale modeling for complex materials. We herein tackle the generation of condensed molecular structures as a refinement—backmapping—of a coarse-grained (CG) structure. Traditional schemes start from a rough coarse-to-fine mapping and perform further energy minimization and molecular dynamics simulations to equilibrate the system. In this study we introduce DeepBackmap: A deep neural network based approach to directly predict equilibrated molecular structures for condensed-phase systems. We use generative adversarial networks to learn the Boltzmann distribution from training data and realize reverse mapping by using the CG structure as a conditional input. We apply our method to a challenging condensed-phase polymeric system. We observe that the model trained in a melt has remarkable transferability to the crystalline phase. The combination of data-driven and physics-based aspects of our architecture help reach temperature transferability with only limited training data.
This study introduces DeepBackmap: A deep neural network based approach to directly predict equilibrated molecular structures for condensed-phase systems and observes that the model trained in a melt has remarkable transferability to the crystalline phase.
@article{Stieffenhofer_2020,
doi = {10.1088/2632-2153/abb6d4},
url = {https://doi.org/10.1088%2F2632-2153%2Fabb6d4},
year = 2020,
month = {oct},
publisher = {{IOP} Publishing},
volume = {1},
number = {4},
pages = {045014},
author = {Marc Stieffenhofer and Michael Wand and Tristan Bereau},
title = {Adversarial reverse mapping of equilibrated condensed-phase molecular structures},
journal = {Machine Learning: Science and Technology}
}