Machine learning prediction of critical transition and system collapse
- URL: http://arxiv.org/abs/2012.01545v1
- Date: Wed, 2 Dec 2020 21:38:54 GMT
- Title: Machine learning prediction of critical transition and system collapse
- Authors: Ling-Wei Kong, Hua-Wei Fan, Celso Grebogi, Ying-Cheng Lai
- Abstract summary: We develop a free, machine learning based solution to two problems in nonlinear dynamics.
We demonstrate that, when the machine is trained in the normal functioning regime with a chaotic attractor, the transition point can be predicted accurately.
For a parameter drift through the critical point, the machine with the input parameter channel is able to predict not only that the system will be in a transient state, but also the average transient time before the final collapse.
- Score: 0.0
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: To predict a critical transition due to parameter drift without relying on
model is an outstanding problem in nonlinear dynamics and applied fields. A
closely related problem is to predict whether the system is already in or if
the system will be in a transient state preceding its collapse. We develop a
model free, machine learning based solution to both problems by exploiting
reservoir computing to incorporate a parameter input channel. We demonstrate
that, when the machine is trained in the normal functioning regime with a
chaotic attractor (i.e., before the critical transition), the transition point
can be predicted accurately. Remarkably, for a parameter drift through the
critical point, the machine with the input parameter channel is able to predict
not only that the system will be in a transient state, but also the average
transient time before the final collapse.
Related papers
- Unsupervised learning for anticipating critical transitions [0.249660468924754]
We articulate a framework combining a variational autoencoder (VAE) and reservoir computing to address this challenge.
In particular, the driving factor is detected from time series using the VAE in an unsupervised-learning fashion.
We demonstrate power of prototypical unsupervised learning scheme using dynamical systems including the Kuramoto-Sivashinsky system.
arXiv Detail & Related papers (2025-01-02T23:57:23Z) - Learning Physics From Video: Unsupervised Physical Parameter Estimation for Continuous Dynamical Systems [49.11170948406405]
State-of-the-art in automatic parameter estimation from video is addressed by training supervised deep networks on large datasets.
We propose a method to estimate the physical parameters of any known, continuous governing equation from single videos.
arXiv Detail & Related papers (2024-10-02T09:44:54Z) - Apparent delay of the Kibble-Zurek mechanism in quenched open systems [0.0]
We report a new intermediate regime in the quench time, $tau_q$, separating the usual validity of the Kibble-Zurek mechanism (KZM)
It manifests in the power-law scaling of the transition time with $tau_q$ as the system appears to enter the adiabatic regime.
This intermediate regime emerges due to the dissipation preventing the system from freezing in the impulse regime.
arXiv Detail & Related papers (2024-07-18T11:48:37Z) - Machine-learning parameter tracking with partial state observation [0.0]
Complex and nonlinear dynamical systems often involve parameters that change with time, accurate tracking of which is essential to tasks such as state estimation, prediction, and control.
We develop a model-free and fully data-driven framework to accurately track time-varying parameters from partial state observation in real time.
Low- and high-dimensional, Markovian and non-Markovian nonlinear dynamical systems are used to demonstrate the power of the machine-learning based parameter-tracking framework.
arXiv Detail & Related papers (2023-11-15T17:39:25Z) - Machine learning in and out of equilibrium [58.88325379746631]
Our study uses a Fokker-Planck approach, adapted from statistical physics, to explore these parallels.
We focus in particular on the stationary state of the system in the long-time limit, which in conventional SGD is out of equilibrium.
We propose a new variation of Langevin dynamics (SGLD) that harnesses without replacement minibatching.
arXiv Detail & Related papers (2023-06-06T09:12:49Z) - Particle-Based Score Estimation for State Space Model Learning in
Autonomous Driving [62.053071723903834]
Multi-object state estimation is a fundamental problem for robotic applications.
We consider learning maximum-likelihood parameters using particle methods.
We apply our method to real data collected from autonomous vehicles.
arXiv Detail & Related papers (2022-12-14T01:21:05Z) - Formal Controller Synthesis for Markov Jump Linear Systems with
Uncertain Dynamics [64.72260320446158]
We propose a method for synthesising controllers for Markov jump linear systems.
Our method is based on a finite-state abstraction that captures both the discrete (mode-jumping) and continuous (stochastic linear) behaviour of the MJLS.
We apply our method to multiple realistic benchmark problems, in particular, a temperature control and an aerial vehicle delivery problem.
arXiv Detail & Related papers (2022-12-01T17:36:30Z) - Supervised DKRC with Images for Offline System Identification [77.34726150561087]
Modern dynamical systems are becoming increasingly non-linear and complex.
There is a need for a framework to model these systems in a compact and comprehensive representation for prediction and control.
Our approach learns these basis functions using a supervised learning approach.
arXiv Detail & Related papers (2021-09-06T04:39:06Z) - Anticipating synchronization with machine learning [1.0958014189747356]
In applications of dynamical systems, it is desired to predict the onset of synchronization.
We develop a prediction framework that is model free and fully data driven.
We demonstrate the machine-learning based framework using representative chaotic models and small network systems.
arXiv Detail & Related papers (2021-03-13T03:51:48Z) - Using Data Assimilation to Train a Hybrid Forecast System that Combines
Machine-Learning and Knowledge-Based Components [52.77024349608834]
We consider the problem of data-assisted forecasting of chaotic dynamical systems when the available data is noisy partial measurements.
We show that by using partial measurements of the state of the dynamical system, we can train a machine learning model to improve predictions made by an imperfect knowledge-based model.
arXiv Detail & Related papers (2021-02-15T19:56:48Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.