Skip to main content
SpringerLink
Log in

Surrogate molecular dynamics simulation model for dielectric constants with ensemble neural networks

MRS Communications volume 12, pages 966–974 (2022)Cite this article

Abstract

We develop ensemble neural networks (ENN) that serve as computationally fast surrogate models of Stockmayer fluid molecular dynamics (MD) simulations for determining the dielectric constants of polar solvents and NaCl solutions. The ENNs are trained using 50-times less data than is used to calculate the dielectric constants from MD simulations. The predictions of ENNs trained on this small amount of data and using batch normalization or bagging are in relatively good agreement with the full MD results. These ENN methods are thus able to extract reliable values from statistically noisy data.

Graphical abstract

This is a preview of subscription content, access via your institution.

Access options

Buy single article

Instant access to the full article PDF.

39,95 €

Price includes VAT (Finland)

Figure 1
Figure 2
Figure 3

Data availability

The training data can be found in the Supplementary Information.

References

  1. F. Noé, A. Tkatchenko, K.-R. Müller, C. Clementi, Annu. Rev. Phys. Chem. 71, 361 (2020)

    Article  Google Scholar 

  2. J. Wang, S. Olsson, C. Wehmeyer, A. Pérez, N.E. Charron, G. de Fabritiis, F. Noé, C. Clementi, ACS Cent. Sci. 5, 755 (2019)

    Article  CAS  Google Scholar 

  3. A. Krishnamoorthy et al., Phys. Rev. Lett. 126, 216403 (2021)

    Article  CAS  Google Scholar 

  4. H. Ghorbanfekr, J. Behler, F.M. Peeters, J. Phys. Chem. Lett. 11, 7363 (2020)

    Article  CAS  Google Scholar 

  5. Q.Q. Gu, L.F. Zhang, J. Feng, Sci. Bull. 67, 29 (2022)

    Article  CAS  Google Scholar 

  6. J.E. Floyd, J.R. Lukes, J. Chem. Phys. 156, 184114 (2022)

    Article  CAS  Google Scholar 

  7. L.K. Hansen, P. Salamon, IEEE Trans. Pattern Anal. Mach. Intell. 12, 993 (1990)

    Article  Google Scholar 

  8. S. Hashem, B. Schmeiser, Y. Yih, in Proceedings of 1994 IEEE International Conference on Neural Networks (ICNN'94), pp. 1507 (1994)

  9. H.M. Le, L.M. Raff, J. Phys. Chem. A 114, 45 (2010)

    Article  CAS  Google Scholar 

  10. S.K. Singh, K.K. Bejagam, Y. An, S.A. Deshmukh, J. Phys. Chem. A 123, 5190 (2019)

    Article  CAS  Google Scholar 

  11. D.A.R.S. Latino, F.F.M. Freitas, J. Aires-De-Sousa, F.M.S. Silva Fernandes, Int. J. Quantum Chem. 107, 2120 (2007)

    Article  CAS  Google Scholar 

  12. C.J. Shock, M.J. Stevens, A.L. Frischknecht, I. Nakamura, J. Phys. Chem. B 124, 4598 (2020)

    Article  CAS  Google Scholar 

  13. S. Ioffe, C. Szegedy. https://arxiv.org/abs/1502.03167 (2015)

  14. L. Breiman, Mach. Learn. 24, 123 (1996)

    Google Scholar 

  15. G. Parascandolo, H. Huttunen, T. Virtanen, Taming the waves: sine as activation function in deep neural networks (2017)

  16. S. Plimpton, J. Comput. Phys. 117, 1 (1995)

    Article  CAS  Google Scholar 

  17. J. Grunenberg, Computational Spectroscopy: Methods, Experiments and Applications (Wiley-VCH, Weinheim, 2010)

    Book  Google Scholar 

  18. T. Gao, Z. Qian, H. Chen, R. Shahbazian-Yassar, I. Nakamura, Mol. Syst. Des. Eng. 7, 260 (2022)

    Article  CAS  Google Scholar 

  19. S. Hashem, B. Schmeiser, IEEE Trans. Neural Netw. 6, 792 (1995)

    Article  CAS  Google Scholar 

  20. D.J. Reid, Economica 35, 431 (1968)

    Article  Google Scholar 

  21. S. Hashem, Neural Netw. 10, 599 (1997)

    Article  Google Scholar 

  22. I. Goodfellow, Y. Bengio, A. Courville, Deep learning, adaptive computation and machine learning

  23. F. Chollet et al., https://keras.io (2015)

  24. W.M. Haynes, D.R. Lide, T.J. Bruno, CRC Handbook of Chemistry and Physics (CRC Press, Baca Raton, 2016)

    Book  Google Scholar 

  25. G.G. Raju, Dielectrics in Electric Fields, 2nd edn. (CRC Press Taylor & Francis Group, Boca Raton, 2016)

    Google Scholar 

Download references

Acknowldgments

We are grateful to the High-Performance Computing Shared Facility, Superior, at MTU, and Sandia National Labs (SNL) High-Performance Computing at SNL for their essential support.

Funding

This material is based upon work supported by the Faculty Early Career Development Program of the National Science Foundation under grant DMR-1944211 and Michigan Tech’s doctoral finishing fellowship. This work was performed, in part, at the Center for Integrated Nanotechnologies, an Office of Science User Facility operated for the U.S. Department of Energy (DOE) Office of Science. Sandia National Laboratories is a multimission laboratory managed and operated by National Technology & Engineering Solutions of Sandia, LLC, a wholly owned subsidiary of Honeywell International, Inc., for the U.S. DOE’s National Nuclear Security Administration under contract DE-NA-0003525.

Author information

Authors and Affiliations

  1. Department of Physics, Michigan Technological University, Houghton, MI, 49931, USA

    Tong Gao, Cameron J. Shock & Issei Nakamura

  2. Center for Integrated Nanotechnologies, Sandia National Laboratories, Albuquerque, NM, 87185, USA

    Mark J. Stevens & Amalie L. Frischknecht

Authors
  1. Tong Gao
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Cameron J. Shock
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Mark J. Stevens
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Amalie L. Frischknecht
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Issei Nakamura
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Issei Nakamura.

Ethics declarations

Conflict of interest

All authors declare that they have no conflict of interest.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Supplementary Information

Below is the link to the electronic supplementary material.

Supplementary file1 (DOCX 10108 kb)

Rights and permissions

Springer Nature or its licensor holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and Permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Gao, T., Shock, C.J., Stevens, M.J. et al. Surrogate molecular dynamics simulation model for dielectric constants with ensemble neural networks. MRS Communications 12, 966–974 (2022). https://doi.org/10.1557/s43579-022-00283-5

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1557/s43579-022-00283-5

Keywords

  • Dielectric properties
  • Machine learning
  • Water
  • Simulation
  • Statistical methods

Search

Navigation