Abstract:
Physics-Informed Neural Networks (PINNs) have received much attention recently due to their potential for high-performance computations for complex physical systems, including data-based computing, systems with unknown parameters, and others. The idea of PINNs is to approximate the equations and boundary and initial conditions through a loss function for a neural network. PINNs combine the efficiency of data-based prediction with the accuracy and insights provided by the physical models. However, applications of these methods to predict the long-term evolution of systems with little friction, such as many systems encountered in space exploration, oceanography/climate, and many other fields, need extra care as the errors tend to accumulate, and the results may quickly become unreliable.
We provide a solution to the problem of data-based computation of Hamiltonian systems utilizing symmetry methods. Many Hamiltonian systems with symmetry can be written as a Lie-Poisson system, where the underlying symmetry defines the Poisson bracket. For data-based computing of such systems, we design the Lie-Poisson neural networks (LPNets). We consider the Poisson bracket structure primary and require it to be satisfied exactly, whereas the Hamiltonian, only known from physics, can be satisfied approximately. By design, the method preserves all special integrals of the bracket (Casimirs) to machine precision. LPNets yield an efficient and promising computational method for many particular cases, such as rigid body or satellite motion (the case of SO(3) group), Kirchhoff's equations for an underwater vehicle (SE(3) group), and others.
Joint work with Chris Eldred (Sandia National Lab), Francois Gay-Balmaz (NTU Singapore), and Sophia Huraka (U Alberta). The work was partially supported by an NSERC Discovery grant.
Bio:
Dr. Vakhtang Putkaradze received his PhD from the University of Copenhagen, Denmark, and held faculty positions in New Mexico, Colorado State University, and, most recently, at the University of Alberta, where he was a Centennial Professor between 2012-2019. From 2019 to 2022, he led the science and tech part of the Transformation Team at ATCO Ltd, first as a Senior Director and then Vice-President. He is now back at the University of Alberta, where he is currently studying applications of geometric mechanics to neural networks, in particular, efficient computations of Hamiltonian systems using data-based techniques. His main topic of interest is using geometric methods in mechanics and various applications. He has received numerous prizes and awards for research and teaching, including Humboldt Fellowship, Senior JSPS fellowship, CAIMS-Fields industrial math prize and G. I. Zaslavsky prize.
