Skip to main content
Journal cover image

Force Field for Water Based on Neural Network.

Publication ,  Journal Article
Wang, H; Yang, W
Published in: The journal of physical chemistry letters
June 2018

We developed a novel neural network-based force field for water based on training with high-level ab initio theory. The force field was built based on an electrostatically embedded many-body expansion method truncated at binary interactions. The many-body expansion method is a common strategy to partition the total Hamiltonian of large systems into a hierarchy of few-body terms. Neural networks were trained to represent electrostatically embedded one-body and two-body interactions, which require as input only one and two water molecule calculations at the level of ab initio electronic structure method CCSD/aug-cc-pVDZ embedded in the molecular mechanics water environment, making it efficient as a general force field construction approach. Structural and dynamic properties of liquid water calculated with our force field show good agreement with experimental results. We constructed two sets of neural network based force fields: nonpolarizable and polarizable force fields. Simulation results show that the nonpolarizable force field using fixed TIP3P charges has already behaved well, since polarization effects and many-body effects are implicitly included due to the electrostatic embedding scheme. Our results demonstrate that the electrostatically embedded many-body expansion combined with neural network provides a promising and systematic way to build next-generation force fields at high accuracy and low computational costs, especially for large systems.

Duke Scholars

Altmetric Attention Stats
Dimensions Citation Stats

Published In

The journal of physical chemistry letters

DOI

EISSN

1948-7185

ISSN

1948-7185

Publication Date

June 2018

Volume

9

Issue

12

Start / End Page

3232 / 3240

Related Subject Headings

  • 51 Physical sciences
  • 34 Chemical sciences
  • 03 Chemical Sciences
  • 02 Physical Sciences
 

Citation

APA
Chicago
ICMJE
MLA
NLM
Wang, H., & Yang, W. (2018). Force Field for Water Based on Neural Network. The Journal of Physical Chemistry Letters, 9(12), 3232–3240. https://doi.org/10.1021/acs.jpclett.8b01131
Wang, Hao, and Weitao Yang. “Force Field for Water Based on Neural Network.The Journal of Physical Chemistry Letters 9, no. 12 (June 2018): 3232–40. https://doi.org/10.1021/acs.jpclett.8b01131.
Wang H, Yang W. Force Field for Water Based on Neural Network. The journal of physical chemistry letters. 2018 Jun;9(12):3232–40.
Wang, Hao, and Weitao Yang. “Force Field for Water Based on Neural Network.The Journal of Physical Chemistry Letters, vol. 9, no. 12, June 2018, pp. 3232–40. Epmc, doi:10.1021/acs.jpclett.8b01131.
Wang H, Yang W. Force Field for Water Based on Neural Network. The journal of physical chemistry letters. 2018 Jun;9(12):3232–3240.
Journal cover image

Published In

The journal of physical chemistry letters

DOI

EISSN

1948-7185

ISSN

1948-7185

Publication Date

June 2018

Volume

9

Issue

12

Start / End Page

3232 / 3240

Related Subject Headings

  • 51 Physical sciences
  • 34 Chemical sciences
  • 03 Chemical Sciences
  • 02 Physical Sciences