Hostname: page-component-848d4c4894-4rdrl Total loading time: 0 Render date: 2024-07-01T19:10:55.118Z Has data issue: false hasContentIssue false
  • English
  • Français

The most robust representations of flow trajectories are Lagrangian coherent structures

Published online by Cambridge University Press:  28 September 2021

Theodore MacMillan Open the ORCID record for Theodore MacMillan [Opens in a new window]  and
David H. Richter Open the ORCID record for David H. Richter [Opens in a new window]
Theodore MacMillan
Affiliation:
Department of Aerospace and Mechanical Engineering, University of Notre Dame, Notre Dame, IN 46656, USA
David H. Richter*
Affiliation:
Department of Civil and Environmental Engineering and Earth Sciences, University of Notre Dame, IN 46656, USA
*
†Email address for correspondence: drichte2@nd.edu
Get access Rights & Permissions [Opens in a new window]

Abstract

What is the most robust way to communicate flow trajectories? To answer this question, we employ two neural networks to respectively deconstruct (the encoder) and reconstruct (the decoder) trajectories, where information is passed between the two networks through a low-dimensional latent space in a set-up known as an autoencoder. To ensure that their communications are robust, we add noise to the coded information passed through this latent space. In the low-noise limit the latent space structures are non-spatial in nature, resembling modes of a principle component analysis (PCA). However, as the signal-to-noise ratio is decreased, we uncover Lagrangian coherent structures (LCS) as the most compact representations which still allow the decoder to accurately reconstruct trajectories. This relationship offers increased interpretability to both PCA and LCS analysis, and helps to bridge the gap between two methods of flow analysis.

JFM classification

Nonlinear Dynamical Systems: Low-dimensional models Nonlinear Dynamical Systems: Pattern formation
Type
JFM Papers
Information
Journal of Fluid Mechanics , Volume 927 , 25 November 2021 , A26
Check for updates
Copyright
© The Author(s), 2021. Published by Cambridge University Press

Access options

Get access to the full version of this content by using one of the access options below. (Log in options will check for institutional or personal access. Content may require purchase if you do not have access.)

References

REFERENCES

Bengio, Y., Courville, A. & Vincent, P. 2013 Representation learning: a review and new perspectives. IEEE Trans. Pattern Anal. Mach. Intell. 35 (8), 1798–1828.CrossRefGoogle ScholarPubMed
Brunton, S.L., Noack, B.R. & Koumoutsakos, P. 2020 Machine learning for fluid mechanics. Annu. Rev. Fluid Mech. 54, 477–508.CrossRefGoogle Scholar
Brunton, S.L., Proctor, J.L., Kutz, J.N. & Bialek, W. 2016 Discovering governing equations from data by sparse identification of nonlinear dynamical systems. Proc. Natl Acad. Sci. USA 113 (15), 3932–3937.CrossRefGoogle ScholarPubMed
Burgess, C.P., Higgins, I., Pal, A., Matthey, L., Watters, N., Desjardins, G. & Lerchner, A. 2018 Understanding disentangling in beta-VAE. arXiv:1804.03599.Google Scholar
Fang, L., Balasuriya, S. & Ouellette, N.T. 2019 Local linearity, coherent structures, and scale-to-scale coupling in turbulent flow. Phys. Rev. Fluids 4 (1), 014501.CrossRefGoogle Scholar
Fang, L. & Ouellette, N.T. 2021 Assessing the information content of complex flows. Phys. Rev. E 103 (2), 23301.CrossRefGoogle ScholarPubMed
Filippi, M., Rypina, I.I., Hadjighasem, A. & Peacock, T. 2021 An optimized-parameter spectral clustering approach to coherent structure detection in geophysical flows. Fluids 6 (1), 39.CrossRefGoogle Scholar
Hadjighasem, A., Farazmand, M., Blazevski, D., Froyland, G. & Haller, G. 2017 A critical comparison of Lagrangian methods for coherent structure detection. Chaos 27 (5), 53104.CrossRefGoogle ScholarPubMed
Hadjighasem, A., Karrasch, D., Teramoto, H. & Haller, G. 2016 A spectral clustering approach to Lagrangian vortex detection. Phys. Rev. E 93 (6), 063107.CrossRefGoogle ScholarPubMed
Haller, G., Hadjighasem, A., Farazmand, M. & Huhn, F. 2016 Defining coherent vortices objectively from the vorticity. J. Fluid Mech. 795, 136–173.Google Scholar
Haller, G. & Yuan, G. 2000 Lagrangian coherent structures and mixing in two-dimensional turbulence. Physica D 147 (3–4), 352–370.CrossRefGoogle Scholar
Higgins, I., Loic, M., Pal, A., Burgess, C., Glorot, X., Botvinick, M., Mohamed, S. & Lerchner, A. 2017 beta-VAE: learning basic visual concepts with a constrained variational framework. In ICLR 2017 – International Conference on Learning Representations, Toulon, France, 24–26 April 2017. ICLR.Google Scholar
Iten, R., Metger, T., Wilming, H., Del Rio, L. & Renner, R. 2020 Discovering physical concepts with neural networks. Phys. Rev. Lett. 124 (1), 10508.CrossRefGoogle ScholarPubMed
Karrasch, D. & Schilling, N. 2020 Fast and robust computation of coherent Lagrangian vortices on very large two-dimensional domains. SMAI J. Comput. Math. 6, 101–124.Google Scholar
Lusch, B., Kutz, J.N. & Brunton, S.L. 2018 Deep learning for universal linear embeddings of nonlinear dynamics. Nat. Commun. 9 (1).CrossRefGoogle ScholarPubMed
Rypina, I.I., Brown, M.G., Beron-Vera, F.J., Koçak, H., Olascoaga, M.J. & Udovydchenkov, I.A. 2007 On the Lagrangian dynamics of atmospheric zonal jets and the permeability of the stratospheric polar vortex. J. Atmos. Sci. 64 (10), 3595–3610.CrossRefGoogle Scholar
Schlueter-Kuck, K.L. & Dabiri, J.O. 2017 Coherent structure colouring: identification of coherent structures from sparse data using graph theory. J. Fluid Mech. 811, 468–486.CrossRefGoogle Scholar
Shadden, S.C., Lekien, F. & Marsden, J.E. 2005 Definition and properties of Lagrangian coherent structures from finite-time Lyapunov exponents in two-dimensional aperiodic flows. Physica D 212 (3–4), 271–304.CrossRefGoogle Scholar
Vieira, G.S., Rypina, I.I. & Allshouse, M.R. 2020 Uncertainty quantification of trajectory clustering applied to ocean ensemble forecasts. Fluids 5 (4), 10–12.CrossRefGoogle Scholar