@article{200246,
  author = {Tom Bertalan and Felix Dietrich and Igor Mesic and IoannisG. Kevrekidis},
  title = {On learning hamiltonian systems from data},
  abstract = { Concise, accurate descriptions of phys. systems through their conserved quantities abound in the natural sciences. In data science, however, current research often focuses on regression problems, without routinely incorpo- rating addnl. assumptions about the system that generated the data. Here, we propose to explore a particular type of underlying structure in the data: Hamiltonian systems, where an "energy" is conserved. Given a collection of observations of such a Hamiltonian system over time, we extract phase space coordinates and a Hamiltonian function of them that acts as the generator of the system dynamics. The approach employs an auto-encoder neural network component to estimate the transformation from observations to the phase space of a Hamiltonian system. An addi- tional neural network component is used to approx. the Hamiltonian function on this constructed space, and the two components are trained simultaneously. As an alternative approach, we also demonstrate the use of Gaussian processes for the estimation of such a Hamiltonian. After two illustrative examples, we extract an underlying phase space as well as the generating Hamiltonian from a collection of movies of a pendulum. The approach is fully data-driven, and does not assume a particular form of the Hamiltonian function. },
  year = {2019},
  journal = {arXiv.org, e-Print Arch., Phys.},
  pages = {1-9},
  publisher = {Cornell University Library},
  url = {https://arxiv.org/abs/1907.12715v1},
  language = {eng},
}