Empirical Classification of Trajectory Data: An Opportunity for the Use of Machine Learning in Molecular Dynamics

B.K. Carpenter, G.S. Ezra,  S. C. Farantos, Z. C. Kramer, and S. Wiggins. Empirical Classification of Trajectory Data: An Opportunity for the Use of Machine Learning in Molecular Dynamics. J. Phys. Chem. B. DOI: 10.1021/acs.jpcb.7b08707

Publication Date (Web): October 2, 2017.
https://pubs.acs.org/doi/abs/10.1021/acs.jpcb.7b08707

SW news Publication picuture #1

This paper uses trajectory data and machine learning approaches to “learn” phase space structures. Classical Hamiltonian trajectories are initiated at random points in phase space on a fixed energy shell of a model two degree of freedom potential, consisting of two interacting minima in an otherwise flat energy plane of infinite extent.  Below the energy of the plane, the dynamics are demonstrably chaotic.  However, most of the work in this paper involves trajectories at a fixed energy that is 1% above that of the plane, in which regime the dynamics exhibit behavior characteristic of chaotic scattering.  The trajectories are analyzed without reference to the potential, as if they had been generated in a typical direct molecular dynamics simulation.  The questions addressed are whether one can recover useful information about the structures controlling the dynamics in phase space from the trajectory data alone, and whether, despite the at least partially chaotic nature of the dynamics, one can make statistically meaningful predictions of trajectory outcomes from initial conditions.  It is found that key unstable periodic orbits, which can be identified on the analytical potential, appear by simple classification of the trajectories, and that the specific roles of these periodic orbits in controlling the dynamics are also readily discerned from the trajectory data alone.  Two different approaches to predicting trajectory outcomes from initial conditions are evaluated, and it is shown that the more successful of them has ~90% success.  The results are compared with those from a simple neural network, which has higher predictive success (97%) but requires the information obtained from the “by-hand” analysis to achieve that level.  Finally, the dynamics, which occur partly on the very flat region of the potential, show characteristics of the much-studied phenomenon called “roaming.” On this potential, it is found that roaming trajectories are effectively “failed” periodic orbits, and that angular momentum can be identified as a key controlling factor, despite the fact that it is not a strictly conserved quantity.  It is also noteworthy that roaming on this potential occurs in the absence of a “roaming saddle,” which has previously been hypothesized to be a necessary feature for roaming to occur.

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out / Change )

Twitter picture

You are commenting using your Twitter account. Log Out / Change )

Facebook photo

You are commenting using your Facebook account. Log Out / Change )

Google+ photo

You are commenting using your Google+ account. Log Out / Change )

Connecting to %s