Machine Learning for Performance Enhancement of Molecular Dynamics Simulations

  • JCS Kadupitiya
  • Geoffrey C. Fox
  • Vikram JadhaoEmail author
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11537)


We explore the idea of integrating machine learning with simulations to enhance the performance of the simulation and improve its usability for research and education. The idea is illustrated using hybrid OpenMP/MPI parallelized molecular dynamics simulations designed to extract the distribution of ions in nanoconfinement. We find that an artificial neural network based regression model successfully learns the desired features associated with the output ionic density profiles and rapidly generates predictions that are in excellent agreement with the results from explicit molecular dynamics simulations. The results demonstrate that the performance gains of parallel computing can be further enhanced by using machine learning.


Machine learning Molecular dynamics simulations Parallel computing Scientific computing Clouds 


  1. 1.
    Abadi, M., et al.: TensorFlow: a system for large-scale machine learning. OSDI 16, 265–283 (2016)Google Scholar
  2. 2.
    Allen, R., Hansen, J.P., Melchionna, S.: Electrostatic potential inside ionic solutions confined by dielectrics: a variational approach. Phys. Chem. Chem. Phys. 3, 4177–4186 (2001)CrossRefGoogle Scholar
  3. 3.
    Boda, D., Gillespie, D., Nonner, W., Henderson, D., Eisenberg, B.: Computing induced charges in inhomogeneous dielectric media: application in a monte carlo simulation of complex ionic systems. Phys. Rev. E 69(4), 046702 (2004)CrossRefGoogle Scholar
  4. 4.
    Botu, V., Ramprasad, R.: Adaptive machine learning framework to accelerate ab initio molecular dynamics. Int. J. Quantum Chem. 115(16), 1074–1083 (2015)CrossRefGoogle Scholar
  5. 5.
    Buitinck, L., et al.: API design for machine learning software: experiences from the scikit-learn project. arXiv:1309.0238 (2013)
  6. 6.
    Butler, K.T., Davies, D.W., Cartwright, H., Isayev, O., Walsh, A.: Machine learning for molecular and materials science. Nature 559(7715), 547 (2018)CrossRefGoogle Scholar
  7. 7.
    Chollet, F., et al.: Keras (2015)Google Scholar
  8. 8.
    Feng, G., Qiao, R., Huang, J., Sumpter, B.G., Meunier, V.: Ion distribution in electrified micropores and its role in the anomalous enhancement of capacitance. ACS Nano 4(4), 2382–2390 (2010)CrossRefGoogle Scholar
  9. 9.
    Ferguson, A.L.: Machine learning and data science in soft materials engineering. J. Phys. Condens. Matter 30(4), 043002 (2017)CrossRefGoogle Scholar
  10. 10.
    Häse, F., Kreisbeck, C., Aspuru-Guzik, A.: Machine learning for quantum dynamics: deep learning of excitation energy transfer properties. Chem. Sci. 8(12), 8419–8426 (2017)CrossRefGoogle Scholar
  11. 11.
    Jadhao, V., Solis, F.J., Olvera de la Cruz, M.: Simulation of charged systems in heterogeneous dielectric media via a true energy functional. Phys. Rev. Lett. 109, 223905 (2012)CrossRefGoogle Scholar
  12. 12.
    Jadhao, V., Solis, F.J., Olvera de la Cruz, M.: A variational formulation of electrostatics in a medium with spatially varying dielectric permittivity. J. Chem. Phys. 138(5), 054119 (2013)CrossRefGoogle Scholar
  13. 13.
    Jing, Y., Jadhao, V., Zwanikken, J.W., Olvera de la Cruz, M.: Ionic structure in liquids confined by dielectric interfaces. J. Chem. Phys. 143(19), 194508 (2015)CrossRefGoogle Scholar
  14. 14.
    Kadupitiya, K., Marru, S., Fox, G.C., Jadhao, V.: Ions in nanoconfinement, December 2017., online on nanoHUB; source code on GitHub at
  15. 15.
    Klimeck, G., McLennan, M., Brophy, S.P., Adams III, G.B., Lundstrom, M.S.: advancing education and research in nanotechnology. Comput. Sci. Eng. 10(5), 17–23 (2008)CrossRefGoogle Scholar
  16. 16.
    Limbach, H.J., Arnold, A., Mann, B.A., Holm, C.: ESPResSo - an extensible simulation package for research on soft matter systems. Comp. Phys. Comm. 174(9), 704–727 (2006)CrossRefGoogle Scholar
  17. 17.
    Liu, J., Qi, Y., Meng, Z.Y., Fu, L.: Self-learning monte carlo method. Phys. Rev. B 95, 041101 (2017)CrossRefGoogle Scholar
  18. 18.
    Luo, G., et al.: IoN distributions near a liquid-liquid interface. Science 311(5758), 216–218 (2006)CrossRefGoogle Scholar
  19. 19.
    Plimpton, S.: Fast parallel algorithms for short-range molecular dynamics. J. Comput. Phys. 117(1), 1–19 (1995)CrossRefGoogle Scholar
  20. 20.
    Rabenseifner, R., Hager, G., Jost, G.: Hybrid MPI/OpenMP parallel programming on clusters of multi-core SMP nodes. In: 2009 17th Euromicro International Conference on Parallel, Distributed and Network-Based Processing, pp. 427–436. IEEE (2009)Google Scholar
  21. 21.
    dos Santos, A.P., Netz, R.R.: Dielectric boundary effects on the interaction between planar charged surfaces with counterions only. J. Chem. Phys. 148(16), 164103 (2018)CrossRefGoogle Scholar
  22. 22.
    Smith, A.M., Lee, A.A., Perkin, S.: The electrostatic screening length in concentrated electrolytes increases with concentration. J. Phys. Chem. Lett. 7(12), 2157–2163 (2016)CrossRefGoogle Scholar
  23. 23.
    Solis, F.J., Jadhao, V., Olvera de la Cruz, M.: Generating true minima in constrained variational formulations via modified lagrange multipliers. Phys. Rev. E 88(5), 053306 (2013)CrossRefGoogle Scholar
  24. 24.
    Spellings, M., Glotzer, S.C.: Machine learning for crystal identification and discovery. AIChE J. 64(6), 2198–2206 (2018)CrossRefGoogle Scholar
  25. 25.
    Zwanikken, J.W., Olvera de la Cruz, M.: Tunable soft structure in charged fluids confined by dielectric interfaces. Proc. Nat. Acad. Sci. 110(14), 5301–5308 (2013)CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  1. 1.Intelligent Systems EngineeringIndiana UniversityBloomingtonUSA

Personalised recommendations