Optimal construction of a fast and accurate polarisable water potential based on multipole moments trained by machine learning

Handley, Chris M.; Hawe, Glenn I.; Kell, Douglas B.; Popelier, Paul L. A.

Abstract

To model liquid water correctly and to reproduce its structural, dynamic and thermodynamic properties warrants models that account accurately for electronic polarisation. We have previously demonstrated that polarisation can be represented by fluctuating multipole moments (derived by quantum chemical topology) predicted by multilayer perceptrons (MLPs) in response to the local structure of the cluster. Here we further develop this methodology of modeling polarisation enabling control of the balance between accuracy, in terms of errors in Coulomb energy and computing time. First, the predictive ability and speed of two additional machine learning methods, radial basis function neural networks (RBFNN) and Kriging, are assessed with respect to our previous MLP based polarisable water models, for water dimer, trimer, tetramer, pentamer and hexamer clusters. Compared to MLPs, we find that RBFNNs achieve a 14–26% decrease in median Coulomb energy error, with a factor 2.5–3 slowdown in speed, whilst Kriging achieves a 40–67% decrease in median energy error with a 6.5–8.5 factor slowdown in speed. Then, these compromises between accuracy and speed are improved upon through a simple multi-objective optimisation to identify Pareto-optimal combinations. Compared to the Kriging results, combinations are found that are no less accurate (at the 90th energy error percentile), yet are 58% faster for the dimer, and 26% faster for the pentamer.

Citation

Handley, C. M., Hawe, G. I., Kell, D. B., & Popelier, P. L. A. (2009). Optimal construction of a fast and accurate polarisable water potential based on multipole moments trained by machine learning. Physical Chemistry Chemical Physics, 11(30), 6365-6376. https://doi.org/10.1039/b905748j

• Journal Article Type: Article
• Acceptance Date: May 1, 2009
• Online Publication Date: Jun 5, 2009
• Publication Date: Aug 14, 2009
• Deposit Date: Aug 13, 2020
• Journal: Physical Chemistry Chemical Physics
• Print ISSN: 1463-9076
• Electronic ISSN: 1463-9084
• Publisher: Royal Society of Chemistry
• Peer Reviewed: Peer Reviewed
• Volume: 11
• Issue: 30
• Pages: 6365-6376
• DOI: https://doi.org/10.1039/b905748j
• Public URL: https://nottingham-repository.worktribe.com/output/4830478
• Publisher URL: https://pubs.rsc.org/en/content/articlelanding/2009/CP/b905748j#!divAbstract