Phase space integrity in neural network models of Hamiltonian dynamics: A Lagrangian descriptor approach

Abstract

We propose Lagrangian Descriptors (LDs) as a diagnostic framework for evaluating neural network models of Hamiltonian systems beyond conventional trajectory-based metrics. Standard error measures quantify short-term predictive accuracy but provide little insight into global geometric structures such as orbits and separatrices. Existing evaluation tools in dissipative systems are inadequate for Hamiltonian dynamics due to fundamental differences in the systems. By constructing probability density functions weighted by LD values, we embed geometric information into a statistical framework suitable for information-theoretic comparison. We benchmark physically constrained architectures (SympNet, HénonNet, Generalized Hamiltonian Neural Networks) against data-driven Reservoir Computing across two canonical systems. For the Duffing oscillator, all models recover the homoclinic orbit geometry with modest data requirements, though their accuracy near critical structures varies. For the three-mode nonlinear Schrödinger equation, however, clear differences emerge: symplectic architectures preserve energy but distort phase-space topology, while Reservoir Computing, despite lacking explicit physical constraints, reproduces the homoclinic structure with high fidelity. These results demonstrate the value of LD-based diagnostics for assessing not only predictive performance but also the global dynamical integrity of learned Hamiltonian models.

40 pages, 22 figures

References in corpus (16)

• Discovering governing equations from data: Sparse identification of nonlinear dynamical systems
• Using Machine Learning to Replicate Chaotic Attractors and Calculate Lyapunov Exponents from Data
• Lagrangian Descriptors: A Method for Revealing Phase Space Structures of General Time Dependent Dynamical Systems
• Data-driven prediction of a multi-scale Lorenz 96 chaotic system using deep learning methods: Reservoir computing, ANN, and RNN-LSTM
• The hidden geometry of ocean flows
• Embedding and Approximation Theorems for Echo State Networks
• A Theoretical Framework for Lagrangian Descriptors
• Echo State Networks trained by Tikhonov least squares are L2(μ) approximators of ergodic dynamical systems
• Learning Hamiltonian dynamics by reservoir computer
• Finding NHIM: Identifying High Dimensional Phase Space Structures in Reaction Dynamics using Lagrangian Descriptors
• Fast neural Poincaré maps for toroidal magnetic fields
• Global dynamics visualisation from Lagrangian Descriptors. Applications to discrete and continuous systems
• Quantifying chaos using Lagrangian descriptors
• Lagrangian Descriptors and the Action Integral of Classical Mechanics
• Model-free Forecasting of Rogue Waves using Reservoir Computing
• Improving the prediction of spatio-temporal chaos by combining parallel reservoir computing with dimensionality reduction