Affiliation:
1. Department of Meteorology University of Reading Reading UK
2. National Centre for Earth Observation Reading UK
3. Department of Computer Science University of Reading Reading UK
4. School of Science and Engineering, Tecnológico de Monterrey Mexico City Mexico
5. Department of Physics and Astronomy “Augusto Righi” University of Bologna Bologna Italy
6. School of Computing Newcastle University Newcastle upon Tyne UK
Abstract
AbstractIn chaotic dynamical systems such as the weather, prediction errors grow faster in some situations than in others. Real‐time knowledge about the error growth could enable strategies to adjust the modelling and forecasting infrastructure on the fly to increase accuracy and/or reduce computation time. For example, one could change the ensemble size, the distribution and type of target observations, and so forth. Local Lyapunov exponents are known indicators of the rate at which very small prediction errors grow over a finite time interval. However, their computation is very expensive: it requires maintaining and evolving a tangent linear model, orthogonalisation algorithms and storing large matrices. In this feasibility study, we investigate the accuracy of supervised machine learning in estimating the current local Lyapunov exponents, from input of current and recent time steps of the system trajectory, as an alternative to the classical method. Thus machine learning is not used here to emulate a physical model or some of its components, but “nonintrusively” as a complementary tool. We test four popular supervised learning algorithms: regression trees, multilayer perceptrons, convolutional neural networks, and long short‐term memory networks. Experiments are conducted on two low‐dimensional chaotic systems of ordinary differential equations, the Rössler and Lorenz 63 models. We find that on average the machine learning algorithms predict the stable local Lyapunov exponent accurately, the unstable exponent reasonably accurately, and the neutral exponent only somewhat accurately. We show that greater prediction accuracy is associated with local homogeneity of the local Lyapunov exponents on the system attractor. Importantly, the situations in which (forecast) errors grow fastest are not necessarily the same as those in which it is more difficult to predict local Lyapunov exponents with machine learning.
Funder
Engineering and Physical Sciences Research Council
National Centre for Earth Observation
The Schmidt Family Foundation
Reference94 articles.
1. Abadi M. Agarwal A. Barham P. Brevdo E. Chen Z. Citro C. Corrado G.S. Davis A. Dean J. Devin M. Ghemawat S. Goodfellow I. Harp A. Irving G. Isard M. Jia Y. Jozefowicz R. Kaiser L. Kudlur M. Levenberg J. Mané D. Monga R. Moore S. Murray D. Olah C. Schuster M. Shlens J. Steiner B. Sutskever I. Talwar K. Tucker P. Vanhoucke V. Vasudevan V. Viégas F. Vinyals O. Warden P. Wattenberg M. Wicke M. Yu Y.andZheng X.(2015)TensorFlow: large‐scale machine learning on heterogeneous systems. Software available fromtensorflow.org.
2. Model and data reduction for data assimilation: Particle filters employing projected forecasts and data with application to a shallow water model
3. Algorithm 898
4. Alman J.andWilliams V.V.(2021)“A refined laser method and faster matrix multiplication”.Proceedings of the 2021 ACM‐SIAM Symposium on Discrete Algorithms (SODA). Philadelphia PA: Society for Industrial and Applied Mathematics pp. 522–539.https://doi.org/10.1137/1.9781611976465.32.
5. Arbenz P.(2016)The QR Algorithm. In “Lecture notes on Numerical Methods for Solving Large Scale Eigenvalue Problems” pages 63‐90.http://people.inf.ethz.ch/arbenz/ewp/lnotes.html.