Using Machine Learning to predict extreme events in the Hénon map

Machine Learning (ML) inspired algorithms provide a flexible set of tools for analyzing and forecasting chaotic dynamical systems. We analyze here the performance of one algorithm for the prediction of extreme events in the two-dimensional Hénon 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 Hénon 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 NT, and the size of the network Np. We observe that in order to maintain a certain accuracy, NT∝exp⁡(2hT) and Np∝exp⁡(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.

[1]  E. Ott.  Chaos in Dynamical Systems: Contents , 2002 .

[2]  Hannah Jeckel,et al.  Learning the space-time phase diagram of bacterial swarm expansion , 2019, Proceedings of the National Academy of Sciences.

[3]  Demis Hassabis,et al.  Mastering the game of Go without human knowledge , 2017, Nature.

[4]  Roger G. Melko,et al.  Machine learning phases of matter , 2016, Nature Physics.

[5]  Daniel W. Davies,et al.  Machine learning for molecular and materials science , 2018, Nature.

[6]  Mw Hirsch,et al.  Chaos In Dynamical Systems , 2016 .

[7]  Jaideep Pathak,et al.  Model-Free Prediction of Large Spatiotemporally Chaotic Systems from Data: A Reservoir Computing Approach. , 2018, Physical review letters.

[8]  Gianluca Bontempi,et al.  Machine Learning Strategies for Time Series Forecasting , 2012, eBISS.

[9]  Jerry Westerweel,et al.  Turbulence transition in pipe flow , 2007 .

[10]  J. Herskowitz,et al.  Proceedings of the National Academy of Sciences, USA , 1996, Current Biology.

[11]  M. Schuld,et al.  Neural Networks Take on Open Quantum Systems , 2019, Physics.

[12]  F. Girosi,et al.  Nonlinear prediction of chaotic time series using support vector machines , 1997, Neural Networks for Signal Processing VII. Proceedings of the 1997 IEEE Signal Processing Society Workshop.

[13]  Jaideep Pathak,et al.  Using machine learning to replicate chaotic attractors and calculate Lyapunov exponents from data. , 2017, Chaos.

[14]  W. Marsden.  I and J , 2012 .

[16]  E. Lorenz.  Deterministic nonperiodic flow , 1963 .

[17]  Hossein Azizpour,et al.  Predictions of turbulent shear flows using deep neural networks , 2019, Physical Review Fluids.

[18]  Haibo He,et al.  Learning from Imbalanced Data , 2009, IEEE Transactions on Knowledge and Data Engineering.

[19]  J. Westerweel,et al.  Finite lifetime of turbulence in shear flows , 2006, Nature.

[20]  M. Hénon,et al.  A two-dimensional mapping with a strange attractor , 1976 .

[21]  B. Eckhardt,et al.  Edge states intermediate between laminar and turbulent dynamics in pipe flow , 2009, Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences.

[22]  David E. Rumelhart,et al.  Predicting the Future: a Connectionist Approach , 1990, Int. J. Neural Syst..

[23]  Heaton T. Jeff,et al.  Introduction to Neural Networks with Java , 2005 .

[24]  Erik Aurell,et al.  Recycling of strange sets: II. Applications , 1990 .