Reservoir computing with error correction: long-term behaviors of stochastic dynamical systems
From MaRDI portal
Publication:6090663
Abstract: The prediction of stochastic dynamical systems and the capture of dynamical behaviors are profound problems. In this article, we propose a data-driven framework combining Reservoir Computing and Normalizing Flow to study this issue, which mimics error modeling to improve the traditional Reservoir Computing performance and takes advantage of both approaches. This model-free method successfully predicts the long-term evolution of stochastic dynamical systems and replicates dynamical behaviors. With few assumptions about the underlying stochastic dynamical systems, we deal with Markov/non-Markov and stationary/non-stationary stochastic processes defined by linear/nonlinear stochastic differential equations or stochastic delay differential equations. We verify the effectiveness of the proposed framework in five experiments, including the Ornstein-Uhlenbeck process, Double-Well system, El Ni~no Southern Oscillation simplified model, and stochastic Lorenz system. Additionally, we explore the noise-induced tipping phenomena and the replication of the strange attractor.
Recommendations
- Seeking optimal parameters for achieving a lightweight reservoir computing: a computational endeavor
- Predicting critical transitions in multiscale dynamical systems using reservoir computing
- Data-driven predictions of the Lorenz system
- Learning Stochastic Dynamical System via Flow Map Operator
- Robust optimization and validation of echo state networks for learning chaotic dynamics
Cites work
- A framework for machine learning of model error in dynamical systems
- A practical method for calculating largest Lyapunov exponents from small data sets
- An introduction to stochastic dynamics
- An Introduction to Variational Autoencoders
- Applied stochastic analysis
- Data-driven approximation of the Koopman generator: model reduction, system identification, and control
- Delay Differential Equations and Applications to Biology
- Detecting stochastic governing laws with observation on stationary distributions
- Deterministic Nonperiodic Flow
- Discovering transition phenomena from data of stochastic dynamical systems with Lévy noise
- Fading memory and the problem of approximating nonlinear operators with Volterra series
- Fading memory echo state networks are universal
- scientific article; zbMATH DE number 5167870 (Why is no real title available?)
- Learning stochastic closures using ensemble Kalman inversion
- Learning stochastic dynamics with statistics-informed neural network
- Liquid state machines: motivation, theory, and applications
- Lévy Processes and Stochastic Calculus
- Machine learning for prediction with missing dynamics
- Maximal stochastic transport in the Lorenz equations
- Nonlinear dynamics and chaos. With applications to physics, biology, chemistry, and engineering
- Normalizing flows for probabilistic modeling and inference
- Optimization and applications of echo state networks with leaky- integrator neurons
- Predicting critical transitions in multiscale dynamical systems using reservoir computing
- Re-visiting the echo state property
- Real-Time Computing Without Stable States: A New Framework for Neural Computation Based on Perturbations
- Reservoir Computing
- Solving inverse stochastic problems from discrete particle observations using the Fokker-Planck equation and physics-informed neural networks
- Stochastic differential equations and applications.
- Supervised learning from noisy observations: combining machine-learning techniques with data assimilation
- Topological analysis and synthesis of chaotic time series
- Using machine learning to predict statistical properties of non-stationary dynamical processes: System climate,regime transitions, and the effect of stochasticity
- Using machine learning to replicate chaotic attractors and calculate Lyapunov exponents from data
Cited in
(5)- scientific article; zbMATH DE number 7306919 (Why is no real title available?)
- Large sampling intervals for learning and predicting chaotic systems with reservoir computing
- Transition path properties for one-dimensional non-Markovian models
- Time series forecasting with delay-based reservoir computing: analysis and optimization
- Strong and weak prediction of stochastic dynamics using reservoir computing
This page was built for publication: Reservoir computing with error correction: long-term behaviors of stochastic dynamical systems
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6090663)
