Learning and Interpreting Potentials for Classical Hamiltonian Systems

We consider the problem of learning an interpretable potential energy function from a Hamiltonian system's trajectories. We address this problem for classical, separable Hamiltonian systems. Our approach first constructs a neural network model of the potential and then applies an equation discovery technique to extract from the neural potential a closed-form algebraic expression. We demonstrate this approach for several systems, including oscillators, a central force problem, and a problem of two charged particles in a classical Coulomb potential. Through these test problems, we show close agreement between learned neural potentials, the interpreted potentials we obtain after training, and the ground truth. In particular, for the central force problem, we show that our approach learns the correct effective potential, a reduced-order model of the system.

[1]  J. Behler Perspective: Machine learning potentials for atomistic simulations. , 2016, The Journal of chemical physics.

[2]  Harish S. Bhat,et al.  A Block Coordinate Descent Proximal Method for Simultaneous Filtering and Parameter Estimation , 2018, ICML.

[3]  Harish S. Bhat,et al.  Equations of mind: Data science for inferring nonlinear dynamics of socio-cognitive systems , 2018, Cognitive Systems Research.

[4]  Christoph H. Lampert,et al.  Learning Equations for Extrapolation and Control , 2018, ICML.

[5]  O. A. von Lilienfeld,et al.  Electronic spectra from TDDFT and machine learning in chemical space. , 2015, The Journal of chemical physics.

[6]  Maneesh Sahani,et al.  Learning interpretable continuous-time models of latent stochastic dynamical systems , 2019, ICML.

[7]  Linan Zhang,et al.  On the Convergence of the SINDy Algorithm , 2018, Multiscale Model. Simul..

[8]  Michele Parrinello,et al.  Generalized neural-network representation of high-dimensional potential-energy surfaces. , 2007, Physical review letters.

[9]  K. Müller,et al.  Machine Learning Predictions of Molecular Properties: Accurate Many-Body Potentials and Nonlocality in Chemical Space , 2015, The journal of physical chemistry letters.

[10]  Nongnuch Artrith,et al.  An implementation of artificial neural-network potentials for atomistic materials simulations: Performance for TiO2 , 2016 .

[11]  Harish S. Bhat,et al.  Nonparametric Adjoint-Based Inference for Stochastic Differential Equations , 2016, 2016 IEEE International Conference on Data Science and Advanced Analytics (DSAA).

[12]  S. Brunton,et al.  Discovering governing equations from data by sparse identification of nonlinear dynamical systems , 2015, Proceedings of the National Academy of Sciences.