Symplectic Gaussian Process Regression of Hamiltonian Flow Maps

Abstract

We present an approach to construct appropriate and efficient emulators for Hamiltonian flow maps. Intended future applications are long-term tracing of fast charged particles in accelerators and magnetic plasma confinement configurations. The method is based on multi-output Gaussian process regression on scattered training data. To obtain long-term stability the symplectic property is enforced via the choice of the matrix-valued covariance function. Based on earlier work on spline interpolation we observe derivatives of the generating function of a canonical transformation. A product kernel produces an accurate implicit method, whereas a sum kernel results in a fast explicit method from this approach. Both correspond to a symplectic Euler method in terms of numerical integration. These methods are applied to the pendulum and the Hénon-Heiles system and results compared to an symmetric regression with orthogonal polynomials. In the limit of small mapping times, the Hamiltonian function can be identified with a part of the generating function and thereby learned from observed time-series data of the system's evolution. Besides comparable performance of implicit kernel and spectral regression for symplectic maps, we demonstrate a substantial increase in performance for learning the Hamiltonian function compared to existing approaches.

24 pages, 9 figures

References in corpus (6)

• Inferring solutions of differential equations using noisy multi-fidelity data
• Learning dynamical systems from data: a simple cross-validation perspective
• Calculation of Superdiffusion for the Chirikov-Taylor Model
• Toroidal regularization of the guiding center Lagrangian
• An overview of the escape dynamics in the Henon-Heiles Hamiltonian system
• Quasi-geometric integration of guiding-center orbits in piecewise linear toroidal fields

Cited by in corpus (7)

• Symplectic integration of learned Hamiltonian systems
• Gaussian Process Port-Hamiltonian Systems: Bayesian Learning with Physics Prior
• Variational Learning of Euler-Lagrange Dynamics from Data
• Physically Consistent Learning of Conservative Lagrangian Systems with Gaussian Processes
• Hamiltonian Neural Networks with Automatic Symmetry Detection
• Learning Hamiltonian Dynamics with Reproducing Kernel Hilbert Spaces and Random Features
• Machine learning of continuous and discrete variational ODEs with convergence guarantee and uncertainty quantification