Learning Hamiltonian neural Koopman operator and simultaneously sustaining and discovering conservation law

MOE Frontiers Center for Brain Science and State Key Laboratory of Medical Neurobiology, Fudan University, Shanghai 200032, China (Dated: June 5, 2024) Accurately finding and predicting dynamics based on the observational data with noise perturbations is of paramount significance but still a major challenge presently. Here, for the Hamiltonian mechanics, we propose the Hamiltonian Neural Koopman Operator (HNKO), integrating the knowledge of mathematical physics in learning the Koopman operator, and making it automatically sustain and even discover the conservation laws. We demonstrate the outperformance of the HNKO and its extension using a number of representative physical systems even with hundreds or thousands of freedoms. Our results suggest that feeding the prior knowledge of the underlying system and the mathematical theory appropriately to the learning framework can reinforce the capability of machine learning in solving physical problems. Although progresses have been learning and the Koopman operator theory, we outstandingly achieved, these frameworks, which either articulate a framework to efficiently and robustly learn enlarge the network complexity or overfit the noisy data the Hamiltonian dynamics based solely on the observational during the training stage to decrease the loss, are suffered data even with noise perturbations.