AI-Lorenz: A physics-data-driven framework for black-box and gray-box identification of chaotic systems with symbolic regression
Authors:
Preprint
Abstract
Discovering mathematical models that characterize the observed behavior of dynamical systems remains a major challenge, especially for systems in a chaotic regime. The challenge is even greater when the physics underlying such systems is not yet understood, and scientific inquiry must solely rely on empirical data. Driven by the need to fill this gap, we develop a framework that learns mathematical expressions modeling complex dynamical behaviors by identifying differential equations from noisy and sparse observable data. We train a small neural network to learn the dynamics of a system, its rate of change in time, and missing model terms, which are used as input for a symbolic regression algorithm to autonomously distill the explicit mathematical terms. This, in turn, enables us to predict the future evolution of the dynamical behavior. The performance of this framework is validated by recovering the right-hand sides and unknown terms of certain complex, chaotic systems such as the well-known Lorenz system, a six-dimensional hyperchaotic system, and the non-autonomous Sprott chaotic system, and comparing them with their known analytical expressions.Keywords
All Related Versions
This publication has 38 references indexed in Scilit:
- A multi-scale transition matrix approach to chaotic time seriesChaos, Solitons & Fractals, 2023
- Sparse dynamical system identification with simultaneous structural parameters and initial condition estimationChaos, Solitons & Fractals, 2022
- Theory of functional connections applied to quadratic and nonlinear programming under equality constraintsJournal of Computational and Applied Mathematics, 2022
- Physics-informed neural networks for the point kinetics equations for nuclear reactor dynamicsAnnals of Nuclear Energy, 2022
- A machine learning based control of chaotic systemsChaos, Solitons & Fractals, 2021
- Bayesian system ID: optimal management of parameter, model, and measurement uncertaintyNonlinear Dynamics, 2020
- Genetic programming as a means for programming computers by natural selectionStatistics and Computing, 1994
- Global bifurcations in Rayleigh-Bénard convection. Experiments, empirical maps and numerical bifurcation analysisPhysica D: Nonlinear Phenomena, 1994
- Model identification of a spatiotemporally varying catalytic reactionAIChE Journal, 1993
- Nonlinear signal processing and system identification: applications to time series from electrochemical reactionsChemical Engineering Science, 1990