Machine-learning construction of a model for a macroscopic fluid variable using the delay-coordinate of a scalar observable

DOI10.3934/DCDSS.2020352MaRDI QIDQ830040zbMATH OpenOpenAlexFDO

Authors Kengo Nakai, Yoshitaka Saiki

Publication date 7 May 2021

Published in Discrete and Continuous Dynamical Systems. Series S (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1903.05770

zbMATH Keywords

chaotic invariant sethigh-dimensional attractormachine learningNavier-Stokes equationsreservoir flow

Mathematics Subject Classification ID

Dynamical systems in fluid mechanics, oceanography and meteorology (37N10) Numerical chaos (65P20) Learning and adaptive systems in artificial intelligence (68T05) Navier-Stokes equations for incompressible viscous fluids (76D05) Basic methods in fluid mechanics (76M99)

Abstract: We construct a data-driven dynamical system model for a macroscopic variable the Reynolds number of a high-dimensionally chaotic fluid flow by training its scalar time-series data. We use a machine-learning approach, the reservoir computing for the construction of the model, and do not use the knowledge of a physical process of fluid dynamics in its procedure. It is confirmed that an inferred time-series obtained from the model approximates the actual one in each of various time-intervals, and that some characteristics of the chaotic invariant set mimic the actual ones. We investigate the appropriate choice of the delay-coordinate, especially the delay-time and the dimension, which enables us to construct a model having a relatively high-dimensional attractor easily.

Recommendations

• Using machine learning to replicate chaotic attractors and calculate Lyapunov exponents from data
• Numerical model construction with closed observables
• On explaining the surprising success of reservoir computing forecaster of chaos? The universal machine learning dynamical system with contrast to VAR and DMD
• Modeling chaotic systems: dynamical equations vs machine learning approach
• Reservoir computing for forecasting large spatiotemporal dynamical systems

Cites work

• An experimental unification of reservoir computing methods
• Detection of generalized synchronization using echo state networks
• Embedology
• scientific article; zbMATH DE number 3810550 (Why is no real title available?)
• scientific article; zbMATH DE number 3551792 (Why is no real title available?)
• scientific article; zbMATH DE number 2222127 (Why is no real title available?)
• Real-Time Computing Without Stable States: A New Framework for Neural Computation Based on Perturbations
• Reservoir computing approaches to recurrent neural network training
• Using machine learning to replicate chaotic attractors and calculate Lyapunov exponents from data

Cited in

(4)

• Numerical model construction with closed observables
• Combining machine learning and data assimilation to forecast dynamical systems from noisy partial observations
• Constructing differential equations using only a scalar time-series about continuous time chaotic dynamics
• Machine learning prediction of the Madden-Julian oscillation using reservoir computing

This page was built for publication: Machine-learning construction of a model for a macroscopic fluid variable using the delay-coordinate of a scalar observable

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q830040)