Nonlinear system identification employing automatic differentiation (original) (raw)

Abstract

An optimization based state and parameter estimation method is presented where the required Jacobian matrix of the cost function is computed via automatic differentiation. Automatic differentiation evaluates the programming code of the cost function and provides exact values of the derivatives. In contrast to numerical differentiation it is not suffering from approximation errors and compared to symbolic differentiation it is more convenient to use, because no closed analytic expressions are required. Furthermore, we demonstrate how to generalize the parameter estimation scheme to delay differential equations, where estimating the delay time requires attention.

Loading...

Loading Preview

Sorry, preview is currently unavailable. You can download the paper by clicking the button above.

References (36)

  1. Listing 1: Simple Python example demonstrating the derivation of the (sparse) Jacobian of the function H(w) usind the automatic differentiation tool ADOL-C. (w ) : 5 h = np . z e r o s ( 3 , d t y p e =w . d t y p e )
  2. # T r a c e H( w ) 14 # ---------- i n t 25 w = np . a r r a y ( [ -2 . , 3 . , 1 . , -4 . ] )
  3. References
  4. R.H. Clayton, O. Bernus, E.M. Cherry, H. Dierckx, F.H. Fenton, L. Mirabella, S.V. Panfilov, F.B. Sachse, G. Seeman, H. Zhang, Models of cardiac tissue electrophysiology: Progress, challenges and open questions, Prog. Biophys. Mol. Biol. 104, 22-48 (2011).
  5. U. Parlitz, L. Junge and L. Kocarev, Synchronization based parameter estimation from time series, Phys. Rev. E 54, 6253-6529 (1996).
  6. H. U. Voss, J. Timmer and J. Kurths, Nonlinear dynamical system identification from uncertain and indirect measurements, Int. J. Bifurcation and Chaos 14, 1905-1933 (2004)
  7. D. Ghosh and S. Banerjee, Adaptive scheme for synchronization-based multiparameter estimation from a single chaotic time series and its applications, Phys. Rev. E 78, 056211 (2008).
  8. H. D. I. Abarbanel, D.R. Creveling, J.M. Jeanne, Estimation of parameters in nonlinear systems using balanced synchronization, Phys. Rev. E 77, 016208 (2008).
  9. F. Sorrentino and E. Ott, Using synchronization of chaos to identify the dynamics of unknown systems Chaos 19, 033108 (2009).
  10. I. G. Szendro, M. A. Rodríguez and J. M. López, On the problem of data assimilation by means of synchronization, J. Geophys. Res. 114, D20109 (2009).
  11. W. Yu, G. Chen, J. Cao, J. Lü and U. Parlitz, Parameter identification of dynamical systems from time series, Phys. Rev. E 75, 067201 (2007).
  12. D. Yu and U. Parlitz, Estimating parameters by autosynchronization with dynamic restrictions, Phys. Rev. E 77, 066221 (2008).
  13. D. Ghosh, Nonlinear-observerbased synchronization scheme for multiparameter estimation, EPL 84, 40012 (2008).
  14. D. Fairhurst, I. Tyukin, H. Nijmeijer and C. van Leeuwen, Observers for Canonic Models of Neural Oscillators, Math. Model. Nat. Phenom. 5(3), 146-185 (2010).
  15. D.R. Creveling, P.E. Gill, H. D. I. Abarbanel, State and parameter estimation in nonlinear systems as an optimal tracking problem, Phys. Lett. A 372, 2640-2644 (2008).
  16. J.C. Quinn, P.H. Bryant, D. R. Creveling, S. R. Klein, and H. D. I. Abarbanel, Parameter and state estimation of experimental chaotic systems using synchronization, Phys. Rev. E 80, 016201 (2009).
  17. H. D. I. Abarbanel, D. R. Creveling, R. Farsian and M. Kostuk, Dynamical State and Parameter Estimation, SIAM J. Appl. Dyn. Syst. 8, 1341-1381 (2009).
  18. H.D.I. Abarbanel,Effective actions for statistical data assimilation, Phys. Lett. A 373, 4044404 (2009).
  19. J.C. Quinn, H.D.I. Abarbanel, State and parameter estimation using Monte Carlo evaluation of path integrals, Q. J. R. Meteorol. Soc. 136 (652), 1855-1867 (2010).
  20. H.D.I. Abarbanel, M. Kostuk and W. Whartenby, Data assimilation with regularized nonlinear instabilities, Q J. R. Meteorol. Soc. 136 (648), 769-783 (2010).
  21. J. Bröcker, On Variational Data Assimilation in Continuous Time, Q. J. R. Meteorol. Soc. 136, 1906-1919 (2010).
  22. J. Schumann-Bischoff and U. Parlitz, State and parameter estimation using unconstrained optimization, Phys. Rev. E 84, 056214 (2011).
  23. J. Bröcker and I. Szendro Sensitivity And Out-Of-Sample Error of Continuous Time Data Assimilation, Q. J. R. Meteorol. Soc. 138, 785-801 (2012).
  24. K. Levenberg, A Method for the Solution of Certain Problems in Least Squares, Quart. Appl. Math. 2, 164-168 (1944).
  25. D. Marquardt, An Algorithm for Least-Squares Estimation of Nonlinear Parameters, SIAM J. Appl. Math. 11, 431-441 (1963).
  26. M. I. A. Lourakis, Sparse Non-linear Least Squares Optimization for Geometric Vision, European Conference on Computer Vision 2, 43-56 (2010). http://dx.doi.org/10.1007/978-3-642-15552-9\_4 and http://www.ics.forth.gr/ ~lourakis/sparseLM/
  27. L. B. Rall, Automatic Differentiation: Techniques and Applications, Lecture Notes in Computer Science 120 (1981).
  28. A. Walther and A. Griewank, Getting started with ADOL-C, in U. Naumann and O. Schenk, Combinatorial Scientific Computing, Chapman- Hall CRC Computational Science, 181-202 (2012).
  29. A. Griewank, D. Juedes and J. Utke, Algorithm 755: ADOL-C: A Package for the Automatic Differentiation of Algorithms Written in C/ C++, ACM Trans. on Math. Softw. 22, 131-167 (1996).
  30. ColPack: http://www.cscapes.org/coloringpage/software.htm (accessed: October 16, 2012)
  31. E. N. Lorenz, Predictability -A problem partly solved, ECMWF, Reading, Berkshire, UK, Proceedings of the Seminar on Predictability 1, 1-18 (1996).
  32. M. C. Mackey and L. Glass, Oscillation and chaos in physiological control systems, Science 197, 287-289 (1977).
  33. Numpy: http://numpy.scipy.org/ (accessed: October 16, 2012)
  34. Pyadolc: https://github.com/b45ch1/pyadolc (accessed: October 16, 2012)
  35. A Python wrapper for sparseLM and a Python-C implementation of the estimation method for ODEs can be downloaded from http: //www.bmp.ds.mpg.de/pysparselm.html and http://www.bmp.ds.mpg.de/pyodefit.html (Gnu General Public License Version 3, 29 June 2007)
  36. P.V. Kuptsov and U. Parlitz, Theory and Computation of Covariant Lyapunov Vectors, J. Nonlinear Sci. 22, 727-762 (2012).