Using machine learning to predict extreme events in the Hénon map

DOI10.1063/1.5121844MaRDI QIDQ5218150zbMATH OpenOpenAlexWikidataFDO

Authors Martin Lellep, Jonathan Prexl, Moritz Linkmann, Bruno Eckhardt

Publication date 28 February 2020

Published in Chaos: An Interdisciplinary Journal of Nonlinear Science (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/2002.10268

Mathematics Subject Classification ID

Topological entropy (37B40) Simulation of dynamical systems (37M05) Learning and adaptive systems in artificial intelligence (68T05) Artificial neural networks and deep learning (68T07)

Abstract: Machine Learning (ML) inspired algorithms provide a flexible set of tools for analyzing and forecasting chaotic dynamical systems. We here analyze the performance of one algorithm for the prediction of extreme events in the two-dimensional H'enon map at the classical parameters. The task is to determine whether a trajectory will exceed a threshold after a set number of time steps into the future. This task has a geometric interpretation within the dynamics of the H'enon map, which we use to gauge the performance of the neural networks that are used in this work. We analyze the dependence of the success rate of the ML models on the prediction time $T$ , the number of training samples $N_T$ and the size of the network $N_p$. We observe that in order to maintain a certain accuracy, $N_{T}proptoexp(2hT)$ and $N_{p}proptoexp(hT)$, where $h$ is the topological entropy. Similar relations between the intrinsic chaotic properties of the dynamics and ML parameters might be observable in other systems as well.

Recommendations

• Using machine learning to predict extreme events in complex systems
• Predicting observed and hidden extreme events in complex nonlinear dynamical systems with partial observations and short training time series
• Neural machine-based forecasting of chaotic dynamics
• Using machine learning to replicate chaotic attractors and calculate Lyapunov exponents from data
• Learning chaotic dynamics by neural networks

Cites work

• A two-dimensional mapping with a strange attractor
• Chaos in Dynamical Systems
• Deep learning
• Deterministic Nonperiodic Flow
• Edge states intermediate between laminar and turbulent dynamics in pipe flow
• Transition to turbulence in shear flows
• Turbulence transition in pipe flow
• Using machine learning to replicate chaotic attractors and calculate Lyapunov exponents from data

Cited in

(12)

• Extreme events in dynamical systems and random walkers: a review
• Correlation between the Hurst exponent and the maximal Lyapunov exponent: examining some low-dimensional conservative maps
• Output-weighted and relative entropy loss functions for deep learning precursors of extreme events
• A filtered Hénon map
• Automated flare prediction using extreme learning machine
• A Comparative Study on Machine Learning Techniques for Intense Convective Rainfall Events Forecasting
• Interpreted machine learning in fluid dynamics: explaining relaminarisation events in wall-bounded shear flows
• Predicting observed and hidden extreme events in complex nonlinear dynamical systems with partial observations and short training time series
• Machine learning, alignment of covariant Lyapunov vectors, and predictability in Rikitake’s geomagnetic dynamo model
• Using machine learning to predict extreme events in complex systems
• Data driven soliton solution of the nonlinear Schrödinger equation with certain \(\mathcal{PT}\)-symmetric potentials via deep learning
• Using machine learning to predict catastrophes in dynamical systems

This page was built for publication: Using machine learning to predict extreme events in the Hénon map

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5218150)