Abstract
The mathematical concept of chaos was introduced by Edward Lorenz in the early 1960s while attempting to represent atmospheric convection through a two-dimensional fluid flow with an imposed temperature difference in the vertical direction. Since then, chaotic dynamical systems are accepted as the foundation of the meteorological sciences and represent an indispensable testbed for weather and climate forecasting tools. Operational weather forecasting platforms rely on costly partial differential equations (PDE)-based models that run continuously on high performance computing architectures. Machine learning (ML)-based low-dimensional surrogate models can be viewed as a cost-effective solution for such high-fidelity simulation platforms. In this work, we propose an ML method based on Reservoir Computing - Echo State Neural Network (RC-ESN) to accurately predict evolutionary states of chaotic systems. We start with the baseline Lorenz-63 and 96 systems and show that RC-ESN is extremely effective in consistently predicting time series using Pearson’s cross correlation similarity measure. RC-ESN can accurately forecast Lorenz systems for many Lyapunov time units into the future. In a practical numerical example, we applied RC-ESN combined with space-only proper orthogonal decomposition (POD) to build a reduced order model (ROM) that produces sequential short-term forecasts of pollution dispersion over the continental USA region. We use GEOS-CF simulated data to assess our RC-ESN ROM. Numerical experiments show reasonable results for such a highly complex atmospheric pollution system.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsNotes
- 1.
- 2.
Lyapunov time unit is computed based on the reciprocal of the maximum Lyapunov exponent. Like the largest eigenvalue of a given matrix, the largest Lyapunov exponent is responsible for the dominant behavior of a system.
References
Akiba, T., Sano, S., Yanase, T., Ohta, T., Koyama, M.: Optuna: a next-generation hyperparameter optimization framework. In: Proceedings of the 25rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (2019)
Bollt, E.: On explaining the surprising success of reservoir computing forecaster of chaos? the universal machine learning dynamical system with contrasts to VAR and DMD (2020). arXiv:2008.06530
Chattopadhyay, A., Hassanzadeh, P., Subramanian, D.: Data-driven prediction of a multi-scale Lorenz 96 chaotic system using deep learning methods: reservoir computing, ANN, and RNN-LSTM. Nonlinear Process. Geophys. 27, 373–389 (2020). https://doi.org/10.5194/npg-27-373-2020
Costa Nogueira, A., de Sousa Almeida, J.L., Auger, G., Watson, C.D.: Reduced order modeling of dynamical systems using artificial neural networks applied to water circulation. In: Jagode, H., Anzt, H., Juckeland, G., Ltaief, H. (eds.) High Performance Computing, pp. 116–136. Springer International Publishing, Cham (2020)
Gao, Z., Liu, Q., Hesthaven, J.S., Wang, B.S., Don, W.S., Wen, X.: Non-intrusive reduced order modeling of convection dominated flows using artificial neural networks with application to Rayleigh-Taylor instability. Commun. Comput. Phys. 30(1), 97–123 (2021)
Le Digabel, S.: Algorithm 909: Nomad: Nonlinear optimization with the mads algorithm. ACM Trans. Math. Softw. 37(4), 1–15 (2011). https://doi.org/10.1145/1916461.1916468
Lee, K., Carlberg, K.: Model reduction of dynamical systems on nonlinear manifolds using deep convolutional autoencoders. J. Comput. Phys. (2019). https://doi.org/10.1016/j.jcp.2019.108973
Mendible, A., Brunton, S.L., Aravkin, A.Y., Lowrie, W., Kutz, J.N.: Dimensionality Reduction and Reduced Order Modeling for Traveling Wave Physics (2020). arXiv e-prints arXiv:1911.00565v2
Mohan, A., Gaitonde, D.: A deep learning based approach to reduced order modeling for turbulent flow control using LSTM neural networks (2018). arXiv:1804.09269
Nekkanti, A., Schmidt, O.T.: Frequency-time analysis, low-rank reconstruction and denoising of turbulent flows using SPOD (2020). arXiv e-prints arXiv:2011.03644
Nguyen, D., Ouala, S., Drumetz, L., Fablet, R.: EM-like Learning Chaotic Dynamics from Noisy and Partial Observations (2019). arXiv e-prints arXiv:1903.10335
Ozturk, M.C., Xu, D., Principe, J.C.: Analysis and design of echo state networks. Neural Comput. 19(1), 111–138 (2007)
Pathak, J., Hunt, B., Girvan, M., Lu, Z., Ott, E.: Model-free prediction of large spatiotemporally chaotic systems from data: a reservoir computing approach. Phys. Rev. Lett. 120, 024102 (2018)
Pearson, K.: Note on regression and inheritance in the case of two parents. Proc. R. Soc. London. 58, 240–242 (1895)
Stewart, M.: Predicting stock prices with echo state networks. Towards Data Science (2019). https://towardsdatascience.com/predicting-stock-prices-with-echo-state-networks-f910809d23d4
Thornes, T., Düben, P., Palmer, T.: On the use of scale-dependent precision in earth system modelling. Q. J. R. Meteorol. Soc. 143, 897–908 (2017). https://doi.org/10.1002/qj.2974
Vlachas, P.R., Byeon, W., Wan, Z.Y., Sapsis, T.P., Koumoutsakos, P.: Data-driven forecasting of high-dimensional chaotic systems with long short-term memory networks. Proc. R. Soc. A Math. Phys. Eng. Sci. 474(2213), 20170844 (2018). https://doi.org/10.1098/rspa.2017.0844
Vlachas, P.R., et al.: Backpropagation Algorithms and Reservoir Computing in Recurrent Neural Networks for the Forecasting of Complex Spatiotemporal Dynamics (2019). arXiv e-prints arXiv:1910.05266
Wang, Q., Ripamonti, N., Hesthaven, J.: Recurrent neural network closure of parametric pod-galerkin reduced-order models based on the mori-zwanzig formalism (2020). https://doi.org/10.1016/j.jcp.2020.109402
Yildiz, I.B., Jaeger, H., Kiebel, S.J.: Re-visiting the echo state property. Neural Netw. 35, 1–9 (2012)
Acknowledgement
EB acknowledges a UKRI Future Leaders Fellowship for support through the grant MR/T041862/1. FCTC acknowledges the São Paulo Research Foundation (FAPESP) for support through the grant #2019/14597-5.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Appendices
A Non Linear Transformation in RC-ESN Hidden Space
Following the same approach proposed in [3], we defined three options for the nonlinear transformations \(\mathcal {T}\):
B Single Shot RC-ESN Loss Function Minimization
The least-squares problem stated in Eq. 5 aims at finding the reservoir-to-output matrix \(\mathbf {W}_{out}\in \mathbb {R}^{n_{i} \times D}\). We can equivalently solve that problem by writing the following linear system [2]:
where \(\mathbf {X} \in \mathbb {R}^{n_{i} \times N}\) is the matrix that stacks every input data \(\mathbf {x}(t)\) shifted by one time step for all N time steps, and \(\tilde{\mathbf {R}} \in \mathbb {R}^{D \times N}\) is the matrix that stacks every corresponding \(\mathcal {T}\)-transformed hidden states \(\mathbf {\tilde{r}}(t)\). The parameter \(\alpha \) is the ridge regularization, and \(\mathbf {I}\) is the identity matrix.
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Nogueira Jr., A.C., Carvalho, F.C.T., Almeida, J.L.S., Codas, A., Bentivegna, E., Watson, C.D. (2021). Reservoir Computing in Reduced Order Modeling for Chaotic Dynamical Systems. In: Jagode, H., Anzt, H., Ltaief, H., Luszczek, P. (eds) High Performance Computing. ISC High Performance 2021. Lecture Notes in Computer Science(), vol 12761. Springer, Cham. https://doi.org/10.1007/978-3-030-90539-2_4
Download citation
DOI: https://doi.org/10.1007/978-3-030-90539-2_4
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-90538-5
Online ISBN: 978-3-030-90539-2
eBook Packages: Computer ScienceComputer Science (R0)