Deep neural network (DNN) potentials have recently gained popularity in computer simulations of a wide range of molecular systems, from liquids to materials. In this study, we explore the possibility of combining the computational efficiency of the DeePMD framework and the demonstrated accuracy of the MB-pol data-driven, many-body potential to train a DNN potential for large-scale simulations of water across its phase diagram. We find that the DNN potential is able to reliably reproduce the MB-pol results for liquid water, but provides a less accurate description of the vapor–liquid equilibrium properties. This shortcoming is traced back to the inability of the DNN potential to correctly represent many-body interactions. An attempt to explicitly include information about many-body effects results in a new DNN potential that exhibits the opposite performance, being able to correctly reproduce the MB-pol vapor–liquid equilibrium properties, but losing accuracy in the description of the liquid properties. These results suggest that DeePMD-based DNN potentials are not able to correctly “learn” and, consequently, represent many-body interactions, which implies that DNN potentials may have limited ability to predict the properties for state points that are not explicitly included in the training process. The computational efficiency of the DeePMD framework can still be exploited to train DNN potentials on data-driven many-body potentials, which can thus enable large-scale, “chemically accurate” simulations of various molecular systems, with the caveat that the target state points must have been adequately sampled by the reference data-driven many-body potential in order to guarantee a faithful representation of the associated properties.
Skip Nav Destination
A “short blanket” dilemma for a state-of-the-art neural network potential for water: Reproducing experimental properties or the physics of the underlying many-body interactions?
Article navigation
28 February 2023
Research Article|
February 24 2023
A “short blanket” dilemma for a state-of-the-art neural network potential for water: Reproducing experimental properties or the physics of the underlying many-body interactions?

Special Collection:
Machine Learning Hits Molecular Simulations
Yaoguang Zhai
;
Yaoguang Zhai
(Formal analysis, Investigation, Methodology, Software, Validation, Visualization, Writing – original draft, Writing – review & editing)
1
Department of Computer Science and Engineering, University of California San Diego
, La Jolla, California 92093, USA
2
Department of Chemistry and Biochemistry, University of California San Diego
, La Jolla, California 92093, USA
Search for other works by this author on:
Alessandro Caruso
;
Alessandro Caruso
(Formal analysis, Investigation, Methodology, Software, Validation, Visualization, Writing – original draft, Writing – review & editing)
2
Department of Chemistry and Biochemistry, University of California San Diego
, La Jolla, California 92093, USA
Search for other works by this author on:
Sigbjørn Løland Bore
;
Sigbjørn Løland Bore
(Formal analysis, Investigation, Methodology, Software, Validation, Visualization, Writing – original draft, Writing – review & editing)
2
Department of Chemistry and Biochemistry, University of California San Diego
, La Jolla, California 92093, USA
Search for other works by this author on:
Zhishang Luo
;
Zhishang Luo
(Methodology, Software, Validation, Visualization, Writing – original draft, Writing – review & editing)
2
Department of Chemistry and Biochemistry, University of California San Diego
, La Jolla, California 92093, USA
Search for other works by this author on:
Francesco Paesani
Francesco Paesani
a)
(Conceptualization, Formal analysis, Funding acquisition, Investigation, Methodology, Project administration, Supervision, Validation, Visualization, Writing – original draft, Writing – review & editing)
2
Department of Chemistry and Biochemistry, University of California San Diego
, La Jolla, California 92093, USA
3
Materials Science and Engineering, University of California San Diego
, La Jolla, California 92093, USA
4
San Diego Supercomputer Center, University of California San Diego
, La Jolla, California 92093, USA
a)Author to whom correspondence should be addressed: fpaesani@ucsd.edu
Search for other works by this author on:
a)Author to whom correspondence should be addressed: fpaesani@ucsd.edu
Note: This paper is part of the JCP Special Topic on Machine Learning Hits Molecular Simulations.
J. Chem. Phys. 158, 084111 (2023)
Article history
Received:
January 17 2023
Accepted:
January 31 2023
Citation
Yaoguang Zhai, Alessandro Caruso, Sigbjørn Løland Bore, Zhishang Luo, Francesco Paesani; A “short blanket” dilemma for a state-of-the-art neural network potential for water: Reproducing experimental properties or the physics of the underlying many-body interactions?. J. Chem. Phys. 28 February 2023; 158 (8): 084111. https://doi.org/10.1063/5.0142843
Download citation file:
Sign in
Don't already have an account? Register
Sign In
You could not be signed in. Please check your credentials and make sure you have an active account and try again.
Sign in via your Institution
Sign in via your InstitutionPay-Per-View Access
$40.00