# American Institute of Mathematical Sciences

2015, 2(2): 247-265. doi: 10.3934/jcd.2015005

## A kernel-based method for data-driven koopman spectral analysis

 1 United Technologies Research Center, 411 Silver Lane, East Hartford, CT 06118, United States 2 Dept. of Mechanical and Aerospace Engineering, Princeton University, Princeton, NJ 08544 3 Department of Chemical and Biological Engineering & PACM, Princeton University, Princeton, NJ 08544, United States

Received  February 2015 Revised  February 2016 Published  May 2016

A data-driven, kernel-based method for approximating the leading Koopman eigenvalues, eigenfunctions, and modes in problems with high-dimensional state spaces is presented. This approach uses a set of scalar observables (functions that map a state to a scalar value) that are defined implicitly by the feature map associated with a user-defined kernel function. This circumvents the computational issues that arise due to the number of functions required to span a sufficiently rich'' subspace of all possible scalar observables in such applications. We illustrate this method on two examples: the first is the FitzHugh-Nagumo PDE, a prototypical one-dimensional reaction-diffusion system, and the second is a set of vorticity data computed from experimentally obtained velocity data from flow past a cylinder at Reynolds number 413. In both examples, we use the output of Dynamic Mode Decomposition, which has a similar computational cost, as the benchmark for our approach.
Citation: Matthew O. Williams, Clarence W. Rowley, Ioannis G. Kevrekidis. A kernel-based method for data-driven koopman spectral analysis. Journal of Computational Dynamics, 2015, 2 (2) : 247-265. doi: 10.3934/jcd.2015005
##### References:
 [1] S. Bagheri, Koopman-mode decomposition of the cylinder wake,, Journal of Fluid Mechanics, 726 (2013), 596. doi: 10.1017/jfm.2013.249. [2] S. Bagheri, Effects of weak noise on oscillating flows: Linking quality factor, Floquet modes, and Koopman spectrum,, Physics of Fluids, 26 (2014). doi: 10.1063/1.4895898. [3] G. Baudat and F. Anouar, Kernel-based methods and function approximation,, In Proceedings of the International Joint Conference on Neural Networks, 2 (2001), 1244. doi: 10.1109/IJCNN.2001.939539. [4] C. M. Bishop et al, Pattern Recognition and Machine Learning,, Springer, (2006). doi: 10.1007/978-0-387-45528-0. [5] J. P. Boyd, Chebyshev and Fourier Spectral Methods,, Courier Dover Publications, (2001). [6] M. Budišić, R. Mohr and I. Mezić, Applied Koopmanism,, Chaos: An Interdisciplinary Journal of Nonlinear Science, 22 (2012). doi: 10.1063/1.4772195. [7] C. J. Burges, A tutorial on support vector machines for pattern recognition,, Data Mining and Knowledge Discovery, 2 (1998), 121. [8] A. Chatterjee, An introduction to the proper orthogonal decomposition,, Current Science, 78 (2000), 808. [9] K. K. Chen, J. H. Tu and C. W. Rowley, Variants of dynamic mode decomposition: Boundary condition, Koopman, and Fourier analyses,, Journal of Nonlinear Science, 22 (2012), 887. doi: 10.1007/s00332-012-9130-9. [10] R. R. Coifman and S. Lafon, Diffusion maps,, Applied and Computational Harmonic Analysis, 21 (2006), 5. doi: 10.1016/j.acha.2006.04.006. [11] N. Cristianini and J. Shawe-Taylor, An Introduction to Support Vector Machines and Other Kernel-Based Learning Methods,, Cambridge University Press, (2000). doi: 10.1017/CBO9780511801389. [12] C. E. Elmer and E. S. Van Vleck, Spatially discrete FitzHugh-Nagumo equations,, SIAM Journal on Applied Mathematics, 65 (2005), 1153. doi: 10.1137/S003613990343687X. [13] P. Gaspard and S. Tasaki, Liouvillian dynamics of the {Hopf} bifurcation,, Physical Review E, 64 (2001). doi: 10.1103/PhysRevE.64.056232. [14] M. S. Hemati, M. O. Williams and C. W. Rowley, Dynamic mode decomposition for large and streaming datasets,, Physics of Fluids, 26 (2014). doi: 10.1063/1.4901016. [15] P. Holmes, J. L. Lumley, G. Berkooz and C. W. Rowley, Turbulence, Coherent Structures, Dynamical Systems and Symmetry,, Cambridge University Press, (2012). doi: 10.1017/CBO9780511919701. [16] M. R. Jovanović, P. J. Schmid and J. W. Nichols, Sparsity-promoting dynamic mode decomposition,, Physics of Fluids, 26 (2014). [17] J.-N. Juang, Applied System Identification,, Prentice Hall, (1994). [18] B. O. Koopman and J. von Neumann, Dynamical systems of continuous spectra,, Proceedings of the National Academy of Sciences of the United States of America, 18 (1932), 255. doi: 10.1073/pnas.18.3.255. [19] B. O. Koopman, Hamiltonian systems and transformation in Hilbert space,, Proceedings of the National Academy of Sciences of the United States of America, 17 (1931), 315. doi: 10.1073/pnas.17.5.315. [20] J. A. Lee and M. Verleysen, Nonlinear Dimensionality Reduction,, Springer, (2007). doi: 10.1007/978-0-387-39351-3. [21] R. B. Lehoucq, D. C. Sorensen and C. Yang, ARPACK Users' Guide: Solution of Large-Scale Eigenvalue Problems with Implicitly Restarted Arnoldi Methods, volume 6., SIAM, (1998). doi: 10.1137/1.9780898719628. [22] A. Mauroy and I. Mezic, A spectral operator-theoretic framework for global stability,, In 52nd IEEE Conference on Decision and Control, (2013), 5234. doi: 10.1109/CDC.2013.6760712. [23] I. Mezić, Spectral properties of dynamical systems, model reduction and decompositions,, Nonlinear Dynamics, 41 (2005), 309. doi: 10.1007/s11071-005-2824-x. [24] I. Mezić, Analysis of fluid flows via spectral properties of the Koopman operator,, Annual Review of Fluid Mechanics, 45 (2013), 357. doi: 10.1146/annurev-fluid-011212-140652. [25] C. E. Rasmussen, Gaussian Processes for Machine Learning,, MIT Press, (2006). [26] C. W. Rowley, I. Mezić, S. Bagheri, P. Schlatter and D. S. Henningson, Spectral analysis of nonlinear flows,, Journal of Fluid Mechanics, 641 (2009), 115. doi: 10.1017/S0022112009992059. [27] P. J. Schmid, Dynamic mode decomposition of numerical and experimental data,, Journal of Fluid Mechanics, 656 (2010), 5. doi: 10.1017/S0022112010001217. [28] P. J. Schmid, D. Violato and F. Scarano, Decomposition of time-resolved tomographic PIV,, Experiments in Fluids, 52 (2012), 1567. doi: 10.1007/s00348-012-1266-8. [29] P. J. Schmid, L. Li, M. P. Juniper and O. Pust, Applications of the dynamic mode decomposition,, Theoretical and Computational Fluid Dynamics, 25 (2011), 249. doi: 10.1007/s00162-010-0203-9. [30] B. Scholkopf, The kernel trick for distances,, Advances in Neural Information Processing Systems, (2001), 301. [31] L. Sirovich, Turbulence and the dynamics of coherent structures. part I: Coherent structures,, Quarterly of applied mathematics, 45 (1987), 561. [32] G. Tissot, L. Cordier, N. Benard and B. R. Noack, Model reduction using dynamic mode decomposition,, Comptes Rendus Mćcanique, 342 (2014), 410. doi: 10.1016/j.crme.2013.12.011. [33] J. H. Tu, C. W. Rowley, J. N. Kutz and J. K. Shang, Toward compressed DMD: Spectral analysis of fluid flows using sub-Nyquist-rate PIV data,, Experiments in Fluids, 55 (2014), 1. [34] J. H. Tu, C. W. Rowley, D. M. Luchtenburg, S. L. Brunton and J. N. Kutz, On dynamic mode decomposition: Theory and applications,, Journal of Computational Dynamics, 1 (2014), 391. doi: 10.3934/jcd.2014.1.391. [35] M. O. Williams, I. G. Kevrekidis and C. W. Rowley, A data-driven approximation of the Koopman operator: Extending dynamic mode decomposition,, Journal of Nonlinear Science, 25 (2015), 1307. doi: 10.1007/s00332-015-9258-5. [36] A. Wynn, D. S. Pearson, B. Ganapathisubramani and P. J. Goulart, Optimal mode decomposition for unsteady flows,, Journal of Fluid Mechanics, 733 (2013), 473. doi: 10.1017/jfm.2013.426.

show all references

##### References:
 [1] S. Bagheri, Koopman-mode decomposition of the cylinder wake,, Journal of Fluid Mechanics, 726 (2013), 596. doi: 10.1017/jfm.2013.249. [2] S. Bagheri, Effects of weak noise on oscillating flows: Linking quality factor, Floquet modes, and Koopman spectrum,, Physics of Fluids, 26 (2014). doi: 10.1063/1.4895898. [3] G. Baudat and F. Anouar, Kernel-based methods and function approximation,, In Proceedings of the International Joint Conference on Neural Networks, 2 (2001), 1244. doi: 10.1109/IJCNN.2001.939539. [4] C. M. Bishop et al, Pattern Recognition and Machine Learning,, Springer, (2006). doi: 10.1007/978-0-387-45528-0. [5] J. P. Boyd, Chebyshev and Fourier Spectral Methods,, Courier Dover Publications, (2001). [6] M. Budišić, R. Mohr and I. Mezić, Applied Koopmanism,, Chaos: An Interdisciplinary Journal of Nonlinear Science, 22 (2012). doi: 10.1063/1.4772195. [7] C. J. Burges, A tutorial on support vector machines for pattern recognition,, Data Mining and Knowledge Discovery, 2 (1998), 121. [8] A. Chatterjee, An introduction to the proper orthogonal decomposition,, Current Science, 78 (2000), 808. [9] K. K. Chen, J. H. Tu and C. W. Rowley, Variants of dynamic mode decomposition: Boundary condition, Koopman, and Fourier analyses,, Journal of Nonlinear Science, 22 (2012), 887. doi: 10.1007/s00332-012-9130-9. [10] R. R. Coifman and S. Lafon, Diffusion maps,, Applied and Computational Harmonic Analysis, 21 (2006), 5. doi: 10.1016/j.acha.2006.04.006. [11] N. Cristianini and J. Shawe-Taylor, An Introduction to Support Vector Machines and Other Kernel-Based Learning Methods,, Cambridge University Press, (2000). doi: 10.1017/CBO9780511801389. [12] C. E. Elmer and E. S. Van Vleck, Spatially discrete FitzHugh-Nagumo equations,, SIAM Journal on Applied Mathematics, 65 (2005), 1153. doi: 10.1137/S003613990343687X. [13] P. Gaspard and S. Tasaki, Liouvillian dynamics of the {Hopf} bifurcation,, Physical Review E, 64 (2001). doi: 10.1103/PhysRevE.64.056232. [14] M. S. Hemati, M. O. Williams and C. W. Rowley, Dynamic mode decomposition for large and streaming datasets,, Physics of Fluids, 26 (2014). doi: 10.1063/1.4901016. [15] P. Holmes, J. L. Lumley, G. Berkooz and C. W. Rowley, Turbulence, Coherent Structures, Dynamical Systems and Symmetry,, Cambridge University Press, (2012). doi: 10.1017/CBO9780511919701. [16] M. R. Jovanović, P. J. Schmid and J. W. Nichols, Sparsity-promoting dynamic mode decomposition,, Physics of Fluids, 26 (2014). [17] J.-N. Juang, Applied System Identification,, Prentice Hall, (1994). [18] B. O. Koopman and J. von Neumann, Dynamical systems of continuous spectra,, Proceedings of the National Academy of Sciences of the United States of America, 18 (1932), 255. doi: 10.1073/pnas.18.3.255. [19] B. O. Koopman, Hamiltonian systems and transformation in Hilbert space,, Proceedings of the National Academy of Sciences of the United States of America, 17 (1931), 315. doi: 10.1073/pnas.17.5.315. [20] J. A. Lee and M. Verleysen, Nonlinear Dimensionality Reduction,, Springer, (2007). doi: 10.1007/978-0-387-39351-3. [21] R. B. Lehoucq, D. C. Sorensen and C. Yang, ARPACK Users' Guide: Solution of Large-Scale Eigenvalue Problems with Implicitly Restarted Arnoldi Methods, volume 6., SIAM, (1998). doi: 10.1137/1.9780898719628. [22] A. Mauroy and I. Mezic, A spectral operator-theoretic framework for global stability,, In 52nd IEEE Conference on Decision and Control, (2013), 5234. doi: 10.1109/CDC.2013.6760712. [23] I. Mezić, Spectral properties of dynamical systems, model reduction and decompositions,, Nonlinear Dynamics, 41 (2005), 309. doi: 10.1007/s11071-005-2824-x. [24] I. Mezić, Analysis of fluid flows via spectral properties of the Koopman operator,, Annual Review of Fluid Mechanics, 45 (2013), 357. doi: 10.1146/annurev-fluid-011212-140652. [25] C. E. Rasmussen, Gaussian Processes for Machine Learning,, MIT Press, (2006). [26] C. W. Rowley, I. Mezić, S. Bagheri, P. Schlatter and D. S. Henningson, Spectral analysis of nonlinear flows,, Journal of Fluid Mechanics, 641 (2009), 115. doi: 10.1017/S0022112009992059. [27] P. J. Schmid, Dynamic mode decomposition of numerical and experimental data,, Journal of Fluid Mechanics, 656 (2010), 5. doi: 10.1017/S0022112010001217. [28] P. J. Schmid, D. Violato and F. Scarano, Decomposition of time-resolved tomographic PIV,, Experiments in Fluids, 52 (2012), 1567. doi: 10.1007/s00348-012-1266-8. [29] P. J. Schmid, L. Li, M. P. Juniper and O. Pust, Applications of the dynamic mode decomposition,, Theoretical and Computational Fluid Dynamics, 25 (2011), 249. doi: 10.1007/s00162-010-0203-9. [30] B. Scholkopf, The kernel trick for distances,, Advances in Neural Information Processing Systems, (2001), 301. [31] L. Sirovich, Turbulence and the dynamics of coherent structures. part I: Coherent structures,, Quarterly of applied mathematics, 45 (1987), 561. [32] G. Tissot, L. Cordier, N. Benard and B. R. Noack, Model reduction using dynamic mode decomposition,, Comptes Rendus Mćcanique, 342 (2014), 410. doi: 10.1016/j.crme.2013.12.011. [33] J. H. Tu, C. W. Rowley, J. N. Kutz and J. K. Shang, Toward compressed DMD: Spectral analysis of fluid flows using sub-Nyquist-rate PIV data,, Experiments in Fluids, 55 (2014), 1. [34] J. H. Tu, C. W. Rowley, D. M. Luchtenburg, S. L. Brunton and J. N. Kutz, On dynamic mode decomposition: Theory and applications,, Journal of Computational Dynamics, 1 (2014), 391. doi: 10.3934/jcd.2014.1.391. [35] M. O. Williams, I. G. Kevrekidis and C. W. Rowley, A data-driven approximation of the Koopman operator: Extending dynamic mode decomposition,, Journal of Nonlinear Science, 25 (2015), 1307. doi: 10.1007/s00332-015-9258-5. [36] A. Wynn, D. S. Pearson, B. Ganapathisubramani and P. J. Goulart, Optimal mode decomposition for unsteady flows,, Journal of Fluid Mechanics, 733 (2013), 473. doi: 10.1017/jfm.2013.426.
 [1] Steven L. Brunton, Joshua L. Proctor, Jonathan H. Tu, J. Nathan Kutz. Compressed sensing and dynamic mode decomposition. Journal of Computational Dynamics, 2015, 2 (2) : 165-191. doi: 10.3934/jcd.2015002 [2] Jonathan H. Tu, Clarence W. Rowley, Dirk M. Luchtenburg, Steven L. Brunton, J. Nathan Kutz. On dynamic mode decomposition: Theory and applications. Journal of Computational Dynamics, 2014, 1 (2) : 391-421. doi: 10.3934/jcd.2014.1.391 [3] Jiang Xie, Junfu Xu, Celine Nie, Qing Nie. Machine learning of swimming data via wisdom of crowd and regression analysis. Mathematical Biosciences & Engineering, 2017, 14 (2) : 511-527. doi: 10.3934/mbe.2017031 [4] Stefan Klus, Christof Schütte. Towards tensor-based methods for the numerical approximation of the Perron--Frobenius and Koopman operator. Journal of Computational Dynamics, 2016, 3 (2) : 139-161. doi: 10.3934/jcd.2016007 [5] Siwei Yu, Jianwei Ma, Stanley Osher. Geometric mode decomposition. Inverse Problems & Imaging, 2018, 12 (4) : 831-852. doi: 10.3934/ipi.2018035 [6] Jae-Hong Pyo, Jie Shen. Normal mode analysis of second-order projection methods for incompressible flows. Discrete & Continuous Dynamical Systems - B, 2005, 5 (3) : 817-840. doi: 10.3934/dcdsb.2005.5.817 [7] Stefan Klus, Péter Koltai, Christof Schütte. On the numerical approximation of the Perron-Frobenius and Koopman operator. Journal of Computational Dynamics, 2016, 3 (1) : 51-79. doi: 10.3934/jcd.2016003 [8] Rakesh Pilkar, Erik M. Bollt, Charles Robinson. Empirical mode decomposition/Hilbert transform analysis of postural responses to small amplitude anterior-posterior sinusoidal translations of varying frequencies. Mathematical Biosciences & Engineering, 2011, 8 (4) : 1085-1097. doi: 10.3934/mbe.2011.8.1085 [9] Ahmad Deeb, A. Hamdouni, Dina Razafindralandy. Comparison between Borel-Padé summation and factorial series, as time integration methods. Discrete & Continuous Dynamical Systems - S, 2016, 9 (2) : 393-408. doi: 10.3934/dcdss.2016003 [10] Chuandong Li, Fali Ma, Tingwen Huang. 2-D analysis based iterative learning control for linear discrete-time systems with time delay. Journal of Industrial & Management Optimization, 2011, 7 (1) : 175-181. doi: 10.3934/jimo.2011.7.175 [11] Mickaël D. Chekroun, Jean Roux. Homeomorphisms group of normed vector space: Conjugacy problems and the Koopman operator. Discrete & Continuous Dynamical Systems - A, 2013, 33 (9) : 3957-3980. doi: 10.3934/dcds.2013.33.3957 [12] Annalisa Pascarella, Alberto Sorrentino, Cristina Campi, Michele Piana. Particle filtering, beamforming and multiple signal classification for the analysis of magnetoencephalography time series: a comparison of algorithms. Inverse Problems & Imaging, 2010, 4 (1) : 169-190. doi: 10.3934/ipi.2010.4.169 [13] Guoqiang Wang, Zhongchen Wu, Zhongtuan Zheng, Xinzhong Cai. Complexity analysis of primal-dual interior-point methods for semidefinite optimization based on a parametric kernel function with a trigonometric barrier term. Numerical Algebra, Control & Optimization, 2015, 5 (2) : 101-113. doi: 10.3934/naco.2015.5.101 [14] Earl Berkson. Fourier analysis methods in operator ergodic theory on super-reflexive Banach spaces. Electronic Research Announcements, 2010, 17: 90-103. doi: 10.3934/era.2010.17.90 [15] Nikita Kalinin, Mikhail Shkolnikov. Introduction to tropical series and wave dynamic on them. Discrete & Continuous Dynamical Systems - A, 2018, 38 (6) : 2827-2849. doi: 10.3934/dcds.2018120 [16] Mingbao Cheng, Shuxian Xiao, Guosheng Liu. Single-machine rescheduling problems with learning effect under disruptions. Journal of Industrial & Management Optimization, 2018, 14 (3) : 967-980. doi: 10.3934/jimo.2017085 [17] Simone Cacace, Maurizio Falcone. A dynamic domain decomposition for the eikonal-diffusion equation. Discrete & Continuous Dynamical Systems - S, 2016, 9 (1) : 109-123. doi: 10.3934/dcdss.2016.9.109 [18] Daijun Jiang, Hui Feng, Jun Zou. Overlapping domain decomposition methods for linear inverse problems. Inverse Problems & Imaging, 2015, 9 (1) : 163-188. doi: 10.3934/ipi.2015.9.163 [19] Chuang Peng. Minimum degrees of polynomial models on time series. Conference Publications, 2005, 2005 (Special) : 720-729. doi: 10.3934/proc.2005.2005.720 [20] Ruiqi Li, Yifan Chen, Xiang Zhao, Yanli Hu, Weidong Xiao. Time series based urban air quality predication. Big Data & Information Analytics, 2016, 1 (2&3) : 171-183. doi: 10.3934/bdia.2016003

Impact Factor: