Machine Learning for Performance Enhancement of Molecular Dynamics Simulations
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.
KeywordsMachine learning Molecular dynamics simulations Parallel computing Scientific computing Clouds
- 1.Abadi, M., et al.: TensorFlow: a system for large-scale machine learning. OSDI 16, 265–283 (2016)Google Scholar
- 5.Buitinck, L., et al.: API design for machine learning software: experiences from the scikit-learn project. arXiv:1309.0238 (2013)
- 7.Chollet, F., et al.: Keras (2015)Google Scholar
- 14.Kadupitiya, K., Marru, S., Fox, G.C., Jadhao, V.: Ions in nanoconfinement, December 2017. https://nanohub.org/resources/nanoconfinement, online on nanoHUB; source code on GitHub at https://github.com/softmaterialslab/nanoconfinement-md
- 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