Predicting trajectory behaviour via machine-learned invariant manifolds

Abstract

In this paper, we use support vector machines (SVM) to develop a machine learning framework to discover phase space structures that distinguish between distinct reaction pathways. The SVM model is trained using data from trajectories of Hamilton's equations and works well even with relatively few trajectories. Moreover, this framework is specifically designed to require minimal a priori knowledge of the dynamics in a system. This makes our approach computationally better suited than existing methods for high-dimensional systems and systems where integrating trajectories is expensive. We benchmark our approach on Chesnavich's CH${}_4^{+}$ Hamiltonian.

References in corpus (17)

• Scikit-learn: Machine Learning in Python
• scikit-image: Image processing in Python
• Machine learning for molecular simulation
• OrbNet: Deep Learning for Quantum Chemistry Using Symmetry-Adapted Atomic-Orbital Features
• Perspective on integrating machine learning into computational chemistry and materials science
• Guest Editorial: Special Topic on Data-enabled Theoretical Chemistry
• Breaking the Coupled Cluster Barrier for Machine Learned Potentials of Large Molecules: The Case of 15-atom Acetylacetone
• Transition manifolds of complex metastable systems: Theory and data-driven computation of effective dynamics
• Permutationally Invariant, Reproducing Kernel-Based Potential Energy Surfaces for Polyatomic Molecules: From Formaldehyde to Acetone
• Multiple Transition States and Roaming in Ion-Molecule Reactions: a Phase Space Perspective
• Roaming dynamics in ion-molecule reactions: phase space reaction pathways and geometrical interpretation
• Neural network approach to time-dependent dividing surfaces in classical reaction dynamics
• The phase space geometry underlying roaming reaction dynamics
• Influence of mass and potential energy surface geometry on roaming in Chesnavich's CH${}_4^{+}$ model
• Reactive Islands for Three Degrees-of-Freedom Hamiltonian Systems
• Transformative Applications of Machine Learning for Chemical Reactions
• Support vector machines for learning reactive islands