Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
158 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
45 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Mori-Zwanzig latent space Koopman closure for nonlinear autoencoder (2310.10745v2)

Published 16 Oct 2023 in cs.LG, math.DS, physics.flu-dyn, and stat.ML

Abstract: The Koopman operator presents an attractive approach to achieve global linearization of nonlinear systems, making it a valuable method for simplifying the understanding of complex dynamics. While data-driven methodologies have exhibited promise in approximating finite Koopman operators, they grapple with various challenges, such as the judicious selection of observables, dimensionality reduction, and the ability to predict complex system behaviors accurately. This study presents a novel approach termed Mori-Zwanzig autoencoder (MZ-AE) to robustly approximate the Koopman operator in low-dimensional spaces. The proposed method leverages a nonlinear autoencoder to extract key observables for approximating a finite invariant Koopman subspace and integrates a non-Markovian correction mechanism using the Mori-Zwanzig formalism. Consequently, this approach yields a closed representation of dynamics within the latent manifold of the nonlinear autoencoder, thereby enhancing the precision and stability of the Koopman operator approximation. Demonstrations showcase the technique's ability to capture regime transitions in the flow around a cylinder. It also provides a low dimensional approximation for Kuramoto-Sivashinsky with promising short-term predictability and robust long-term statistical performance. By bridging the gap between data-driven techniques and the mathematical foundations of Koopman theory, MZ-AE offers a promising avenue for improved understanding and prediction of complex nonlinear dynamics.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (50)
  1. Dynamical systems of continuous spectra. Proceedings of the National Academy of Sciences, 18(3):255–263, 1932.
  2. I. Mezić. Spectral properties of dynamical systems, model reduction and decompositions. Nonlinear Dynamics, 41:309–325, 2005.
  3. Data-driven approximation of the koopman generator: Model reduction, system identification, and control. Physica D: Nonlinear Phenomena, 406:132416, 2020.
  4. Data-driven discovery of Koopman eigenfunctions for control. Machine Learning: Science and Technology, 2(3):035023, 2021.
  5. Koopman invariant subspaces and finite linear representations of nonlinear dynamical systems for control. PloS one, 11(2):e0150171, 2016.
  6. H. Mori. Transport, collective motion, and brownian motion. Progress of theoretical physics, 33(3):423–455, 1965.
  7. R. Zwanzig. Nonlinear generalized langevin equations. Journal of Statistical Physics, 9(3):215–220, 1973.
  8. J. Page and R. R. Kerswell. Koopman analysis of burgers equation. Physical Review Fluids, 3(7):071901, 2018.
  9. Reduced-order representation of near-wall structures in the late transitional boundary layer. Journal of fluid mechanics, 748:278–301, 2014.
  10. Data-driven spectral analysis of the Koopman operator. Applied and Computational Harmonic Analysis, 48(2):599–629, 2020.
  11. Discovering dynamic patterns from infectious disease data using dynamic mode decomposition. International health, 7(2):139–145, 2015.
  12. A data–driven approximation of the koopman operator: Extending dynamic mode decomposition. Journal of Nonlinear Science, 25:1307–1346, 2015.
  13. P. J. Schmid. Dynamic mode decomposition and its variants. Annual Review of Fluid Mechanics, 54:225–254, 2022.
  14. Linearly recurrent autoencoder networks for learning dynamics. SIAM Journal on Applied Dynamical Systems, 18(1):558–593, 2019.
  15. Deep learning for universal linear embeddings of nonlinear dynamics. Nature communications, 9(1):1–10, 2018.
  16. Learning koopman invariant subspaces for dynamic mode decomposition. Advances in Neural Information Processing Systems, 30, 2017.
  17. Learning deep neural network representations for Koopman operators of nonlinear dynamical systems. In 2019 American Control Conference (ACC), pages 4832–4839. IEEE, 2019.
  18. Enhancing predictive capabilities in data-driven dynamical modeling with automatic differentiation: Koopman and neural ode approaches. arXiv preprint arXiv:2310.06790, 2023.
  19. S. Pan and K. Duraisamy. Physics-informed probabilistic learning of linear embeddings of nonlinear dynamics with guaranteed stability. SIAM Journal on Applied Dynamical Systems, 19(1):480–509, 2020.
  20. Residual dynamic mode decomposition: robust and verified koopmanism. Journal of Fluid Mechanics, 955:A21, 2023.
  21. Data-driven learning for the Mori–Zwanzig formalism: A generalization of the koopman learning framework. SIAM Journal on Applied Dynamical Systems, 20(4):2558–2601, 2021.
  22. Regression-based projection for learning Mori–Zwanzig operators. arXiv preprint arXiv:2205.05135, 2022.
  23. Dynamic-mode decomposition and optimal prediction. Physical Review E, 103(1):012201, 2021.
  24. Optimal prediction and the Mori–Zwanzig representation of irreversible processes. Proceedings of the National Academy of Sciences, 97(7):2968–2973, 2000.
  25. Extension of dynamic mode decomposition for dynamic systems with incomplete information based on t-model of optimal prediction. Journal of Computational Physics, 476:111913, 2023.
  26. Optimal prediction with memory. Physica D: Nonlinear Phenomena, 166(3-4):239–257, 2002.
  27. Applied Koopmanism. Chaos: An Interdisciplinary Journal of Nonlinear Science, 22(4), 2012.
  28. Atmospheric turbulence and radio wave propagation. Journal of computational Chemistry, 23(13):1236–1243, 1967.
  29. Model reduction for flow analysis and control. Annual Review of Fluid Mechanics, 49:387–417, 2017.
  30. Time-series learning of latent-space dynamics for reduced-order model closure. Physica D: Nonlinear Phenomena, 405:132368, 2020.
  31. Recurrent neural network closure of parametric POD-Galerkin reduced-order models based on the Mori-Zwanzig formalism. Journal of Computational Physics, 410:109402, 2020.
  32. CD-ROM: Complemented Deep-Reduced order model. Computer Methods in Applied Mechanics and Engineering, 410:115985, 2023.
  33. Three-dimensional coherent structures in a swirling jet undergoing vortex breakdown: stability analysis and empirical mode construction. Journal of fluid mechanics, 679:383–414, 2011.
  34. J. M. Dominy and D. Venturi. Duality and conditional expectations in the Nakajima-Mori-Zwanzig formulation. Journal of Mathematical Physics, 58(8), 2017.
  35. Computing generalized Langevin equations and generalized Fokker–Planck equations. Proceedings of the National Academy of Sciences, 106(27):10884–10889, 2009.
  36. K. K. Lin and F. Lu. Data-driven model reduction, wiener projections, and the koopman-Mori-Zwanzig formalism. Journal of Computational Physics, 424:109864, 2021.
  37. D. P. Kingma and J. Ba. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980, 2014.
  38. Interpretable learning of effective dynamics for multiscale systems. arXiv preprint arXiv:2309.05812, 2023.
  39. A hierarchy of low-dimensional models for the transient and post-transient cylinder wake. Journal of Fluid Mechanics, 497:335–363, 2003.
  40. Nektar++: An open-source spectral/hp element framework. Computer physics communications, 192:205–219, 2015.
  41. An adaptive selective frequency damping method. Physics of Fluids, 27(9), 2015.
  42. G. Sivashinsky. Nonlinear analysis of hydrodynamic instability in laminar flames—i. derivation of basic equations. In Dynamics of Curved Fronts, pages 459–488. Elsevier, 1988.
  43. Order and complexity in the kuramoto-sivashinsky model of weakly turbulent interfaces. Physica D: Nonlinear Phenomena, 23(1-3):265–292, 1986.
  44. Lyapunov exponents of the Kuramoto–Sivashinsky pde. The ANZIAM Journal, 61(3):270–285, 2019.
  45. Concurrent multiparameter learning demonstrated on the Kuramoto–Sivashinsky equation. SIAM Journal on Scientific Computing, 44(5):A2974–A2990, 2022.
  46. Reconstruction, forecasting, and stability of chaotic dynamics from partial data. arXiv preprint arXiv:2305.15111, 2023.
  47. S. Hochreiter and J. Schmidhuber. Long short-term memory. Neural computation, 9(8):1735–1780, 1997.
  48. Y. Lan and I. Mezić. Linearization in the large of nonlinear systems and koopman operator spectrum. Physica D: Nonlinear Phenomena, 242(1):42–53, 2013.
  49. Data-driven modeling and prediction of non-linearizable dynamics via spectral submanifolds. Nature communications, 13(1):872, 2022.
  50. On the lifting and reconstruction of nonlinear systems with multiple invariant sets.
Citations (3)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now
X Twitter Logo Streamline Icon: https://streamlinehq.com

Tweets