Using machine-learning modelling to understand macroscopic dynamics in a system of coupled maps
arXiv:2011.05803 · doi:10.1063/5.0036809
Abstract
Machine learning techniques not only offer efficient tools for modelling dynamical systems from data, but can also be employed as frontline investigative instruments for the underlying physics. Nontrivial information about the original dynamics, which would otherwise require sophisticated ad-hoc techniques, can be obtained by a careful usage of such methods. To illustrate this point, we consider as a case study the macroscopic motion emerging from a system of globally coupled maps. We build a coarse-grained Markov process for the macroscopic dynamics both with a machine learning approach and with a direct numerical computation of the transition probability of the coarse-grained process, and we compare the outcomes of the two analyses. Our purpose is twofold: on the one hand, we want to test the ability of the stochastic machine learning approach to describe nontrivial evolution laws, as the one considered in our study; on the other hand, we aim at gaining some insight into the physics of the macroscopic dynamics by modulating the information available to the network, we are able to infer important information about the effective dimension of the attractor, the persistence of memory effects and the multi-scale structure of the dynamics.
arXiv comment17 pages, 13 figures
References in corpus (32)
- Adam: A Method for Stochastic Optimization
- Hybrid Forecasting of Chaotic Processes: Using Machine Learning in Conjunction with a Knowledge-Based Model
- Analysis of data sets of stochastic systems
- Growth of non-infinitesimal perturbations in turbulence
- Chaos or Noise - Difficulties of a Distinction
- Deep learning to discover and predict dynamics on an inertial manifold
- An extension of the Lyapunov analysis for the predictability problem
- Inferring the dynamics of underdamped stochastic systems
- Controlling Rayleigh-Bénard convection via Reinforcement Learning
- Hyperbolicity and the effective dimension of spatially-extended dissipative systems
- Reconstruction of turbulent data with deep generative models for semantic inpainting from TURB-Rot database
- Covariant Lyapunov vectors
- Properties making a chaotic system a good Pseudo Random Number Generator
- Stochastic parameterization identification using ensemble Kalman filtering combined with expectation-maximization and Newton-Raphson maximum likelihood methods
- Collective Chaos
- Combining Machine Learning with Knowledge-Based Modeling for Scalable Forecasting and Subgrid-Scale Closure of Large, Complex, Spatiotemporal Systems
- The Fokker-Planck Approach to Complex Spatio-Temporal Disordered Systems
- Computing covariant vectors, Lyapunov vectors, Oseledets vectors, and dichotomy projectors: a comparative numerical study
- Remarks on the mean field dynamics of networks of chaotic elements
- Lyapunov analysis captures the collective dynamics of large chaotic systems
- Broken ergodicity and glassy behavior in a deterministic chaotic map
- Macroscopic chaos in globally coupled maps
- Extensive and Sub-Extensive Chaos in Globally-Coupled Dynamical Systems
- Building general Langevin models from discrete data sets
- Langevin equations from experimental data: the case of rotational diffusion in granular media
- Using Machine Learning to Augment Coarse-Grid Computational Fluid Dynamics Simulations
- The Role of Data in Model Building and Prediction: A Survey Through Examples
- A Renormalization Group Approach to Spontaneous Stochasticity
- Effective models and predictability of chaotic multiscale systems via machine learning
- The predictability problem in systems with an uncertainty in the evolution law
- A hybrid model based on deep LSTM for predicting high-dimensional chaotic systems
- Effective equations for reaction coordinates in polymer transport