Sparse identification of quasipotentials via a combined data-driven method

Abstract

The quasipotential function allows for comprehension and prediction of the escape mechanisms from metastable states in nonlinear dynamical systems. This function acts as a natural extension of the potential function for non-gradient systems and it unveils important properties such as the maximum likelihood transition paths, transition rates and expected exit times of the system. Here, we demonstrate how to discover parsimonious equations for the quasipotential directly from data. Leveraging machine learning, we combine two existing data-driven techniques, namely a neural network and a sparse regression algorithm, specifically designed to symbolically describe multistable energy landscapes. First, we employ a vanilla neural network enhanced with a renormalization and rescaling procedure to achieve an orthogonal decomposition of the vector field. Next, we apply symbolic regression to extract the downhill and circulatory components of the decomposition, ensuring consistency with the underlying dynamics. This symbolic reconstruction involves a simultaneous regression that imposes constraints on both the orthogonality condition and the vector field. We implement and benchmark our approach using an archetypal model with a known exact quasipotential, as well as a nanomechanical resonator system. We further demonstrate its applicability to noisy data and to a four-dimensional system. Our model-unbiased analytical forms of the quasipotential is of interest to a wide range of applications aimed at assessing metastability and energy landscapes, serving to parametrically capture the distinctive fingerprint of the fluctuating dynamics.

References in corpus (18)

• Discovering governing equations from data: Sparse identification of nonlinear dynamical systems
• Tipping points in open systems: bifurcation, noise-induced and rate-dependent examples in the climate system
• PySINDy: A comprehensive Python package for robust sparse system identification
• Sparse Identification of Nonlinear Dynamics for Rapid Model Recovery
• Generalisation of the Eyring-Kramers transition rate formula to irreversible diffusion processes
• Model selection for hybrid dynamical systems via sparse regression
• Escape dynamics of active particles in multistable potentials
• Paths of fluctuation induced switching
• The mean shape of transition and first-passage paths
• High-frequency stochastic switching of graphene resonators near room temperature
• Spectral Evidence of Squeezing of a Weakly Damped Driven Nanomechanical Mode
• Ordered Line Integral Methods for Computing the Quasi-potential
• Ritz method for transition paths and quasipotentials of rare diffusive events
• Computing the quasipotential for nongradient SDEs in 3D
• Construction of quasi-potentials for stochastic dynamical systems: an optimization approach
• Hamiltonian reconstruction via ringdown dynamics
• Data-driven reduced order models using invariant foliations, manifolds and autoencoders
• Controlling mean exit time of stochastic dynamical systems based on quasipotential and machine learning