1. Proceedings
  2. I3M
  3. 2019
  4. EMSS
  5. 10.46354/i3m.2019.emss.031

Fast approximations by machine learning: predicting the energy of dimers using convolutional neural networks

  • a Dylan Hennessey  ,
  • b Mariusz Klobukowski  ,
  • c Paul Lu  
  • a Department of Medicine, University of Alberta, Edmonton, Alberta, Canada
  • b Department of Chemistry, University of Alberta, Edmonton, Alberta, Canada
  • c Department of Computing Science, University of Alberta, Edmonton, Alberta, Canada
Cite as
Hennessey D., Klobukowski M., Lu P. (2019). Fast approximations by machine learning: predicting the energy of dimers using convolutional neural networks. Proceedings of the 31st European Modeling & Simulation Symposium (EMSS 2019), pp. 218-225. DOI: https://doi.org/10.46354/i3m.2019.emss.031.

Abstract

We introduce fast approximations by machine learning (FAML) to compute the energy of molecular systems. FAML can be six times faster than a traditional quantum chemistry approach for molecular geometry optimisation, at least for a simple dimer. Hardware accelerators for machine learning (ML) can further improve FAML’s performance. Since the quantum chemistry calculations show poor algorithmic scaling, faster methods that produce a similar level of accuracy to the more rigorous level of quantum theory are important. As a FAML proof-of-concept, we use a convolutional neural network (CNN) to make energy predictions on the F2 molecular dimer system. Training data for the CNN is computed using a quantum chemistry application (i.e., GAMESS) and represented as an image. Using fivefold cross-validation, we find that the predictions made by the CNN provide a good prediction to the theoretical calculations in a fraction of the time.

References

  1. Abadi M., A. Agarwal, P. Barham, E. Brevdo, Z. Chen, C. Citro, G.S. Corrado, A. Davis, J. Dean, M. Devin, S. Ghemawat, I. Goodfellow, A. Harp, G. Irving, M. Isard, Y. Jia, R. Jozefowicz, L. Kaiser, M. Kudlur, J. Levenberg, D. Mane, R. Monga, S. Moore, D. Murray, C. Olah, M. Schuster, J. Shlens, B. Steiner, I. Sutskever, K. Talwar, P. Tucker, V. Vanhoucke, V. Vasudevan, F. Viegas, O. Vinyals, P. Warden, M. Wattenberg, M. Wicke, Y. Yu, and X. Zheng, “TensorFlow: Large-scale machine learning on heterogeneous systems,” 2015, software available from tensorflow.org. [Online]. Available: https://www.tensorflow.org/
  2. Clark T., J. Chandrasekhar, G. Spitznagel, and P.V. Schleyer, “Efficient diffuse function-augmented basis sets for anion calculations. III. The 3-21+G basis set for first-row elements, Li–F,” J. Comp. Chem., vol. 4, pp. 294–301, 1983.
  3. Frisch M.J., J.A. Pople, and J. Binkley, “Self-consistent molecular orbital methods 25. Supplementary functions for Gaussian basis sets,” J. Chem. Phys., vol. 80, pp. 3265–3269, 1984.
  4. Joupii N., C. Young, N. Patil, and D. Patterson, “Indatacenter performance analysis of a tensor processing unit,” in Proceedings of the 44th Annual International Symposium on Computer Architecture, ISCA 2017, Toronto, ON, Canada, June 24-28, 2017, 2017, pp. 1–12.
  5. Kingma D.P. and J. Ba, “Adam: A method for stochastic optimization,” CoRR, vol. abs/1412.6980, 2014. [Online]. Available: http://arxiv.org/abs/1412.6980
  6. Krishnan R., J. Binkley, R. Seeger, and J.A. Pople, “Selfconsistent molecular orbital methods. XX. A basis set for correlated wave functions,” J. Chem. Phys., vol. 72, pp. 650–654, 1980.
  7. Krizhevsky A., I. Sutskever, and G.E. Hinton, “Imagenet classification with deep convolutional neural networks,” in Advances in Neural Information Processing Systems 25, F. Pereira, C. J. C. Burges, L. Bottou, and K. Q. Weinberger, Eds. Curran Associates, Inc., 2012, pp. 1097–1105.
  8. LeCun Y., B. Boser, J.S. Denker, D. Henderson, R.E. Howard, W. Hubbard, and L.D. Jackel, “Backpropagation applied to handwritten zip code recognition,” Neural Comput., vol. 1, no. 4, pp. 541–551, Dec. 1989. [Online]. Available: http://dx.doi.org/10.1162/neco.1989.1.4.541
  9. Montavon G., M. Rupp, V. Gobre, A. Vazquez-Mayagoitia, K. Hansen, A. Tkatchenko, K.-R. Moller, and O.A. von Lilienfeld, “Machine learning of molecular electronic properties in chemical compound space,” New Journal of Physics, vol. 15, no. 9, p. 095003, 2013. [Online]. Available: http://stacks.iop.org/1367-2630/15/i=9/a=095003
  10. Roos B.O., P. Taylor, and P.E.M. Siegbahn, “A complete active space SCF method (CASSCF) using a density matrix formulated super-CI approach,” Chem. Phys., vol. 48, pp. 157–173, 1980.
  11. Schmidt M.W., K.K. Baldridge, J.A. Boatz, S.T. Elbert, M.S. Gordon, J.H. Jensen, S. Koseki, N. Matsunaga, K.A. Nguyen, S. Su, T.L. Windus, M. Dupuis, and J.A. Montgomery, “General atomic and molecular electronic structure system,” J. Comput. Chem., vol. 14, no. 11, pp. 1347–1363, 1993.
  12. Siegbahn P.E.M., J. Almlof, A. Heiberg, and B.O. Roos, “The complete active space SCF (CASSCF) method in a Newton-Raphson formulation with application to the HNO molecule,” J. Chem. Phys., vol. 74, no. 4, pp. 2384–2396, 1981.
  13. Siegbahn P.E.M., A. Heiberg, B.O. Roos, and B. Levy, “A comparison of the super-CI and the Newton-Raphson scheme in the complete active space SCF method,” Phys. Scr., vol. 21, pp. 323–327, 1980.
  14. Sivaraman A., K. Winstein, P. Thaker, and H. Balakrishnan, “An experimental study of the learnability of congestion control,” in Proceedings of the 2014 ACM Conference on SIGCOMM, ser. SIGCOMM ’14. New York, NY, USA: ACM, 2014, pp. 479–490.
  15. Zupan J. and J. Gasteiger, Neural Networks for Chemists: An Introduction. New York, NY, USA: John Wiley & Sons, Inc., 1993.