Computer simulations can provide mechanistic insight into ionic liquids (ILs) and predict the properties of experimentally unrealized ion combinations. However, ILs suffer from a particularly large disparity in the time scales of atomistic and ensemble motion. Coarse-grained models are therefore used in place of costly all-atom simulations, accessing longer time scales and larger systems. Nevertheless, constructing the many-body potential of mean force that defines the structure and dynamics of a coarse-grained system can be complicated and computationally intensive. Machine learning shows great promise for the linked challenges of dimensionality reduction and learning the potential of mean force. To improve the coarse-graining of ILs, we present a neural network model trained on all-atom classical molecular dynamics simulations. The potential of mean force is expressed as two jointly trained neural network interatomic potentials that learn the coupled short-range and many-body long range molecular interactions. These interatomic potentials treat temperature as an explicit input variable to capture its influence on the potential of mean force. The model reproduces structural quantities with high fidelity, outperforms the temperature-independent baseline at capturing dynamics, generalizes to unseen temperatures, and incurs low simulation cost.
Skip Nav Destination
,
,
,
,
,
CHORUS
Article navigation
28 October 2020
Research Article|
October 22 2020
Temperature-transferable coarse-graining of ionic liquids with dual graph convolutional neural networks Available to Purchase
Special Collection:
Machine Learning Meets Chemical Physics
Jurgis Ruza;
Jurgis Ruza
1
Materials Science and Engineering, École Polytechnique Fédérale de Lausanne
, Lausanne, Switzerland
2
Department of Materials Science and Engineering, Massachusetts Institute of Technology
, Cambridge, Massachusetts 02139, USA
Search for other works by this author on:
Wujie Wang;
Wujie Wang
2
Department of Materials Science and Engineering, Massachusetts Institute of Technology
, Cambridge, Massachusetts 02139, USA
Search for other works by this author on:
Daniel Schwalbe-Koda;
Daniel Schwalbe-Koda
2
Department of Materials Science and Engineering, Massachusetts Institute of Technology
, Cambridge, Massachusetts 02139, USA
Search for other works by this author on:
Simon Axelrod;
Simon Axelrod
2
Department of Materials Science and Engineering, Massachusetts Institute of Technology
, Cambridge, Massachusetts 02139, USA
3
Department of Chemistry and Chemical Biology, Harvard University
, Cambridge, Massachusetts 02138, USA
Search for other works by this author on:
William H. Harris;
William H. Harris
2
Department of Materials Science and Engineering, Massachusetts Institute of Technology
, Cambridge, Massachusetts 02139, USA
Search for other works by this author on:
Rafael Gómez-Bombarelli
Rafael Gómez-Bombarelli
a)
2
Department of Materials Science and Engineering, Massachusetts Institute of Technology
, Cambridge, Massachusetts 02139, USA
a)Author to whom correspondence should be addressed: [email protected]
Search for other works by this author on:
Jurgis Ruza
1,2
Wujie Wang
2
Daniel Schwalbe-Koda
2
Simon Axelrod
2,3
William H. Harris
2
Rafael Gómez-Bombarelli
2,a)
1
Materials Science and Engineering, École Polytechnique Fédérale de Lausanne
, Lausanne, Switzerland
2
Department of Materials Science and Engineering, Massachusetts Institute of Technology
, Cambridge, Massachusetts 02139, USA
3
Department of Chemistry and Chemical Biology, Harvard University
, Cambridge, Massachusetts 02138, USA
a)Author to whom correspondence should be addressed: [email protected]
Note: This paper is part of the JCP Special Topic on Machine Learning Meets Chemical Physics.
J. Chem. Phys. 153, 164501 (2020)
Article history
Received:
July 20 2020
Accepted:
October 05 2020
Citation
Jurgis Ruza, Wujie Wang, Daniel Schwalbe-Koda, Simon Axelrod, William H. Harris, Rafael Gómez-Bombarelli; Temperature-transferable coarse-graining of ionic liquids with dual graph convolutional neural networks. J. Chem. Phys. 28 October 2020; 153 (16): 164501. https://doi.org/10.1063/5.0022431
Download citation file:
Pay-Per-View Access
$40.00
Sign In
You could not be signed in. Please check your credentials and make sure you have an active account and try again.
Citing articles via
DeePMD-kit v2: A software package for deep potential models
Jinzhe Zeng, Duo Zhang, et al.
CREST—A program for the exploration of low-energy molecular chemical space
Philipp Pracht, Stefan Grimme, et al.
GPAW: An open Python package for electronic structure calculations
Jens Jørgen Mortensen, Ask Hjorth Larsen, et al.
Related Content
Deep convolutional neural networks for generating atomistic configurations of multi-component macromolecules from coarse-grained models
J. Chem. Phys. (November 2022)
Conductivity prediction model for ionic liquids using machine learning
J. Chem. Phys. (June 2022)
Backmapping coarse-grained macromolecules: An efficient and versatile machine learning approach
J. Chem. Phys. (July 2020)
Benchmarking binding energy calculations for organic structure-directing agents in pure-silica zeolites
J. Chem. Phys. (May 2021)
Single molecule translocation in smectics illustrates the challenge for time-mapping in simulations on multiple scales
J. Chem. Phys. (September 2017)