Abstract
Predicting complex nonlinear turbulent dynamical systems using partial observations is an important topic. Despite the simplicity of the forecast based on the ensemble mean time series, several critical shortcomings in the ensemble mean forecast and using path-wise measurements to quantify the prediction error are illustrated in this article. Then, a new ensemble method is developed for improving the long-range forecast. This new approach utilizes a mixture of the posterior distributions from data assimilation and is more skillful in predicting non-Gaussian statistics and extreme events than the traditional method by simply running the forecast model forward. Next, a systematic framework of improving forecast models is established, aiming at advancing the predictions at all ranges. The starting model in this new framework belongs to a rich class of nonlinear systems with conditional Gaussian structures. These models allow an efficient nonlinear smoother for state estimation using partial observations, which in turn facilitates a rapid parameter estimation based on an expectation–maximization algorithm. Conditioned on the partially observed time series, the nonlinear smoother further advances an efficient backward sampling of the hidden trajectories, the dynamical and statistical characteristics from which allow a systematic quantification of model error through information theory. The sampled trajectories then serve as the recovered observations of the hidden variables that promote the use of general nonlinear data-driven modeling techniques for a further improvement of the forecast model. A low-order model of the layered topographic equations with regime switching and rare events is used as a test example to illustrate this framework.
Similar content being viewed by others
References
Blanchard-Wrigglesworth, E., Bitz, C., Holland, M.: Influence of initial conditions and climate forcing on predicting arctic sea ice. Geophys. Res. Lett. 38(18), 18503 (2011)
Bourke, R.H., Garrett, R.P.: Sea ice thickness distribution in the arctic ocean. Cold Reg. Sci. Technol. 13(3), 259–280 (1987)
Branicki, M., Majda, A.: Quantifying Bayesian filter performance for turbulent dynamical systems through information theory. Commun. Math. Sci 12(5), 901–978 (2014)
Branicki, M., Majda, A.J.: Quantifying uncertainty for predictions with model error in non-Gaussian systems with intermittency. Nonlinearity 25(9), 2543 (2012)
Branicki, M., Majda, A.J.: Dynamic stochastic superresolution of sparsely observed turbulent systems. J. Comput. Phys. 241, 333–363 (2013)
Bushuk, M., Yang, X., Winton, M., Msadek, R., Harrison, M., Rosati, A., Gudgel, R.: The value of sustained ocean observations for sea ice predictions in the barents sea. J. Clim. 32(20), 7017–7035 (2019)
Casdagli, M.: Nonlinear prediction of chaotic time series. Physica D 35(3), 335–356 (1989)
Cavanaugh, N.R., Gershunov, A., Panorska, A.K., Kozubowski, T.J.: The probability distribution of intense daily precipitation. Geophys. Res. Lett. 42(5), 1560–1567 (2015)
Charney, J.G., DeVore, J.G.: Multiple flow equilibria in the atmosphere and blocking. J. Atmos. Sci. 36(7), 1205–1216 (1979)
Chen, N.: Learning nonlinear turbulent dynamics from partial observations via analytically solvable conditional statistics. J. Comput. Phys. (2020). https://doi.org/10.1016/j.jcp.2020.109635
Chen, N., Giannakis, D., Herbei, R., Majda, A.J.: An MCMC algorithm for parameter estimation in signals with hidden intermittent instability. SIAM/ASA J. Uncertain. Quant. 2(1), 647–669 (2014)
Chen, N., Majda, A.: Conditional Gaussian systems for multiscale nonlinear stochastic systems: prediction, state estimation and uncertainty quantification. Entropy 20(7), 509 (2018)
Chen, N., Majda, A.: Predicting observed and hidden extreme events in complex nonlinear dynamical systems with partial observations and short training time series. Chaos Interdiscip. J. Nonlinear Sci. 30(3), 033101 (2020). https://doi.org/10.1063/1.5122199
Chen, N., Majda, A.J.: Predicting the cloud patterns for the boreal summer intraseasonal oscillation through a low-order stochastic model. Math. Clim. Weather Forecast. 1(1), 1–20 (2015)
Chen, N., Majda, A.J.: Predicting the real-time multivariate Madden–Julian oscillation index through a low-order nonlinear stochastic model. Mon. Weather Rev. 143(6), 2148–2169 (2015)
Chen, N., Majda, A.J.: Filtering nonlinear turbulent dynamical systems through conditional Gaussian statistics. Mon. Weather Rev. 144(12), 4885–4917 (2016)
Chen, N., Majda, A.J.: Filtering the stochastic skeleton model for the Madden–Julian oscillation. Mon. Weather Rev. 144(2), 501–527 (2016)
Chen, N., Majda, A.J.: Model error in filtering random compressible flows utilizing noisy Lagrangian tracers. Mon. Weather Rev. 144(11), 4037–4061 (2016)
Chen, N., Majda, A.J.: Beating the curse of dimension with accurate statistics for the Fokker–Planck equation in complex turbulent systems. Proc. Natl. Acad. Sci. 114(49), 12864–12869 (2017)
Chen, N., Majda, A.J.: Efficient statistically accurate algorithms for the Fokker–Planck equation in large dimensions. J. Comput. Phys. 354, 242–268 (2018)
Chen, N., Majda, A.J.: Efficient nonlinear optimal smoothing and sampling algorithms for complex turbulent nonlinear dynamical systems with partial observations. J. Comput. Phys. 410, 109381 (2020)
Chen, N., Majda, A.J., Giannakis, D.: Predicting the cloud patterns of the Madden–Julian oscillation through a low-order nonlinear stochastic model. Geophys. Res. Lett. 41(15), 5612–5619 (2014)
Chen, N., Majda, A.J., Sabeerali, C., Ajayamohan, R.: Predicting monsoon intraseasonal precipitation using a low-order nonlinear stochastic model. J Clim 31, 4403–4427 (2018)
Chen, N., Majda, A.J., Tong, X.T.: Information barriers for noisy Lagrangian tracers in filtering random incompressible flows. Nonlinearity 27(9), 2133 (2014)
Chen, N., Majda, A.J., Tong, X.T.: Noisy Lagrangian tracers for filtering random rotating compressible flows. J. Nonlinear Sci. 25(3), 451–488 (2015)
Chen, N., Majda, A.J., Tong, X.T.: Rigorous analysis for efficient statistically accurate algorithms for solving Fokker–Planck equations in large dimensions. SIAM/ASA J. Uncertain. Quant. 6(3), 1198–1223 (2018)
Cole, J., Barker, H.W., Randall, D., Khairoutdinov, M., Clothiaux, E.E.: Global consequences of interactions between clouds and radiation at scales unresolved by global climate models. Geophys. Res. Lett. 32(6), 06703 (2005)
Cousins, W., Sapsis, T.P.: Quantification and prediction of extreme events in a one-dimensional nonlinear dispersive wave model. Physica D 280, 48–58 (2014)
Dempster, A.P., Laird, N.M., Rubin, D.B.: Maximum likelihood from incomplete data via the EM algorithm. J. R. Stat. Soc. Ser. B (Methodol.) 39(1), 1–22 (1977)
Evensen, G.: Data Assimilation: The Ensemble Kalman Filter. Springer, Berlin (2009)
Farazmand, M., Sapsis, T.P.: Extreme events: mechanisms and prediction. Appl. Mech. Rev. 71(5), 050801 (2019)
Franzke, C., Crommelin, D., Fischer, A., Majda, A.J.: A hidden Markov model perspective on regimes and metastability in atmospheric flows. J. Clim. 21(8), 1740–1757 (2008)
Gardiner, C.W.: Handbook of stochastic methods for physics. In: Chemistry and the Natural Sciences, vol. 13 of Springer Series in Synergetics (2004)
Gardiner, C.W., et al.: Handbook of Stochastic Methods, vol. 3. Springer, Berlin (1985)
Gershgorin, B., Harlim, J., Majda, A.J.: Improving filtering and prediction of spatially extended turbulent systems with model errors through stochastic parameter estimation. J. Comput. Phys. 229(1), 32–57 (2010)
Gershgorin, B., Harlim, J., Majda, A.J.: Test models for improving filtering with model errors through stochastic parameter estimation. J. Comput. Phys. 229(1), 1–31 (2010)
Ghahramani, Z., Hinton, G.E.: Parameter estimation for linear dynamical systems. In: Technical Report CRG-TR-96-2, University of Totronto, Department of Computer Science (1996)
Ghahramani, Z., Roweis, S.T.: Learning nonlinear dynamical systems using an em algorithm. In: Advances in neural information processing systems, pp. 431–437 (1999)
Giannakis, D., Majda, A.J., Horenko, I.: Information theory, model error, and predictive skill of stochastic models for complex nonlinear systems. Physica D 241(20), 1735–1752 (2012)
Harlim, J., Mahdi, A., Majda, A.J.: An ensemble Kalman filter for statistical estimation of physics constrained nonlinear regression models. J. Comput. Phys. 257, 782–812 (2014)
Hendon, H.H., Lim, E., Wang, G., Alves, O., Hudson, D.: Prospects for predicting two flavors of El Niño. Geophys. Res. Lett. 36(19), 19713 (2009)
Hewitt, G., Vassilicos, C., et al.: Prediction of Turbulent Flows. Cambridge University Press, Cambridge (2005)
Houtekamer, P.L., Mitchell, H.L.: Data assimilation using an ensemble Kalman filter technique. Mon. Weather Rev. 126(3), 796–811 (1998)
Ito, K., Ravindran, S.S.: A reduced-order method for simulation and control of fluid flows. J. Comput. Phys. 143(2), 403–425 (1998)
Janjić, T., Bormann, N., Bocquet, M., Carton, J., Cohn, S., Dance, S., Losa, S., Nichols, N., Potthast, R., Waller, J., et al.: On the representation error in data assimilation. Quart. J. R. Meteorol. Soc. (2017)
Kalman, R.E.: A new approach to linear filtering and prediction problems. J. Basic Eng. 82(1), 35–45 (1960)
Kalman, R.E., Bucy, R.S.: New results in linear filtering and prediction theory. J. Basic Eng. 83(1), 95–108 (1961)
Kalnay, E.: Atmospheric Modeling, Data Assimilation and Predictability. Cambridge University Press, Cambridge (2003)
Keating, S.R., Majda, A.J., Smith, K.S.: New methods for estimating ocean eddy heat transport using satellite altimetry. Mon. Weather Rev. 140(5), 1703–1722 (2012)
Keating, S.R., Smith, K.S., Kramer, P.R.: Diagnosing lateral mixing in the upper ocean with virtual tracers: spatial and temporal resolution dependence. J. Phys. Oceanogr. 41(8), 1512–1534 (2011)
Kim, H.M., Webster, P.J., Curry, J.A.: Seasonal prediction skill of ECMWF system 4 and NCEP CFSv2 retrospective forecast for the northern hemisphere winter. Clim. Dyn. 39(12), 2957–2973 (2012)
Kim, H.M., Webster, P.J., Toma, V.E., Kim, D.: Predictability and prediction skill of the MJO in two operational forecasting systems. J. Clim. 27(14), 5364–5378 (2014)
Kleeman, R.: Information theory and dynamical system predictability. Entropy 13(3), 612–649 (2011)
Kloeden, P.E., Platen, E.: Higher-order implicit strong numerical schemes for stochastic differential equations. J. Stat. Phys. 66(1–2), 283–314 (1992)
Kullback, S.: Statistics and Information Theory. Wiley, New York (1959)
Kullback, S.: Letter to the editor: The Kullback–Leibler distance. American Statistician (1987)
Kullback, S., Leibler, R.A.: On information and sufficiency. Ann. Math. Stat. 22(1), 79–86 (1951)
Kumar, A.: Finite samples and uncertainty estimates for skill measures for seasonal prediction. Mon. Weather Rev. 137(8), 2622–2631 (2009)
Kunisch, K., Volkwein, S.: Control of the burgers equation by a reduced-order approach using proper orthogonal decomposition. J. Optim. Theory Appl. 102(2), 345–371 (1999)
Lahoz, W., Khattatov, B., Ménard, R.: Data assimilation and information. In: Data Assimilation, pp. 3–12. Springer (2010)
Law, K., Stuart, A., Zygalakis, K.: Data Assimilation: A Mathematical Introduction, vol. 62. Springer, Berlin (2015)
Lee, C.Y., Tippett, M.K., Sobel, A.H., Camargo, S.J.: Rapid intensification and the bimodal distribution of tropical cyclone intensity. Nat. Commun. 7, 10625 (2016)
Leith, C.: Predictability of climate. Nature 276(5686), 352–355 (1978)
Lermusiaux, P.F.: Data assimilation via error subspace statistical estimation. Part II: middle atlantic bight shelfbreak front simulations and ESSE validation. Mon. Weather Rev. 127(7), 1408–1432 (1999)
Liptser, R.S., Shiryaev, A.N.: Statistics of random processes II: applications. Appl. Math 6 (2001)
Lorenc, A.C.: Analysis methods for numerical weather prediction. Quart. J. R. Meteorol. Soc. 112(474), 1177–1194 (1986)
Lorenz, E.N.: Energy and numerical weather prediction. Tellus 12(4), 364–373 (1960)
Lorenz, E.N.: Deterministic nonperiodic flow. J. Atmos. Sci. 20(2), 130–141 (1963)
Lorenz, E.N.: Section of planetary sciences: the predictability of hydrodynamic flow. Trans. N. Y. Acad. Sci. 25(4 Series II), 409–432 (1963)
Lorenz, E.N.: Predictability: a problem partly solved. In: Proceedings of the Seminar on predictability, vol. 1 (1996)
Majda, A., Chen, N.: Model error, information barriers, state estimation and prediction in complex multiscale systems. Entropy 20(9), 644 (2018)
Majda, A., Wang, X.: Nonlinear dynamics and statistical theories for basic geophysical flows. Cambridge University Press, Cambridge (2006)
Majda, A.J.: Challenges in climate science and contemporary applied mathematics. Commun. Pure Appl. Math. 65(7), 920–948 (2012)
Majda, A.J.: Introduction to Turbulent Dynamical Systems in Complex Systems. Springer, Berlin (2016)
Majda, A.J., Abramov, R., Gershgorin, B.: High skill in low-frequency climate response through fluctuation dissipation theorems despite structural instability. Proc. Natl. Acad. Sci. 107(2), 581–586 (2010)
Majda, A.J., Franzke, C., Crommelin, D.: Normal forms for reduced stochastic climate models. Proc. Natl. Acad. Sci. 106(10), 3649–3653 (2009)
Majda, A.J., Franzke, C., Khouider, B.: An applied mathematics perspective on stochastic modelling for climate. Philos. Trans. R. Soc. A Math. Phys. Eng. Sci. 366(1875), 2427–2453 (2008)
Majda, A.J., Gershgorin, B.: Quantifying uncertainty in climate change science through empirical information theory. Proc. Natl. Acad. Sci. 107(34), 14958–14963 (2010)
Majda, A.J., Gershgorin, B.: Improving model fidelity and sensitivity for complex systems through empirical information theory. Proc. Natl. Acad. Sci. 108(25), 10044–10049 (2011)
Majda, A.J., Gershgorin, B.: Link between statistical equilibrium fidelity and forecasting skill for complex systems with model error. Proc. Natl. Acad. Sci. 108(31), 12599–12604 (2011)
Majda, A.J., Grooms, I.: New perspectives on superparameterization for geophysical turbulence. J. Comput. Phys. 271, 60–77 (2014)
Majda, A.J., Harlim, J.: Filtering Complex Turbulent Systems. Cambridge University Press, Cambridge (2012)
Majda, A.J., Harlim, J.: Physics constrained nonlinear regression models for time series. Nonlinearity 26(1), 201 (2012)
Majda, A.J., Qi, D.: Strategies for reduced-order models for predicting the statistical responses and uncertainty quantification in complex turbulent dynamical systems. SIAM Rev. 60(3), 491–549 (2018)
Majda, A.J., Qi, D., Sapsis, T.P.: Blended particle filters for large-dimensional chaotic dynamical systems. Proc. Natl. Acad. Sci. 111, 7511–7516 (2014)
Majda, A.J., Timofeyev, I., Eijnden, E.V.: Models for stochastic climate prediction. Proc. Natl. Acad. Sci. 96(26), 14687–14691 (1999)
Massonnet, F., Fichefet, T., Goosse, H.: Prospects for improved seasonal arctic sea ice predictions from multivariate data assimilation. Ocean Model. 88, 16–25 (2015)
Molteni, F., Buizza, R., Palmer, T.N., Petroliagis, T.: The ECMWF ensemble prediction system: methodology and validation. Quart. J. R. Meteorol. Soc. 122(529), 73–119 (1996)
Oke, P.R., Sakov, P.: Representation error of oceanic observations for data assimilation. J. Atmos. Ocean. Technol. 25(6), 1004–1017 (2008)
Palmer, T.: The ECMWF ensemble prediction system: looking back (more than) 25 years and projecting forward 25 years. Quart. J. R. Meteoro. Soc. 145, 12–24 (2019)
Qi, D., Majda, A.J.: Predicting fat-tailed intermittent probability distributions in passive scalar turbulence with imperfect models through empirical information theory. Commun. Math. Sci. 14(6), 1687–1722 (2016)
Qi, D., Majda, A.J.: Low-dimensional reduced-order models for statistical response and uncertainty quantification: barotropic turbulence with topography. Physica D 343, 7–27 (2017)
Rauch, H.E., Striebel, C., Tung, F.: Maximum likelihood estimates of linear dynamic systems. AIAA J. 3(8), 1445–1450 (1965)
Rodrigues, R.R., Subramanian, A., Zanna, L., Berner, J.: Enso bimodality and extremes. Geophys. Res. Lett. 46(9), 4883–4893 (2019)
Salmon, R.: Lectures on Geophysical Fluid Dynamics. Oxford University Press, Oxford (1998)
Sapsis, T.P., Majda, A.J.: Blending modified Gaussian closure and non-gaussian reduced subspace methods for turbulent dynamical systems. J. Nonlinear Sci. 23(6), 1039–1071 (2013)
Simonoff, J.S.: Smoothing Methods in Statistics. Springer, Berlin (2012)
Slingo, J., Palmer, T.: Uncertainty in weather and climate prediction. Philos. Trans. R. Soc. A Math. Phys. Eng. Sci. 369(1956), 4751–4767 (2011)
Sundberg, R.: Maximum likelihood theory for incomplete data from an exponential family. Scand. J. Stat. 1(2), 49–58 (1974)
Sundberg, R.: An iterative method for solution of the likelihood equations for incomplete data from exponential families. Commun. Stat. Simul. Comput. 5(1), 55–64 (1976)
Taylor, K.E.: Summarizing multiple aspects of model performance in a single diagram. J. Geophys. Res. Atmos. 106(D7), 7183–7192 (2001)
Toth, Z., Kalnay, E.: Ensemble forecasting at ncep and the breeding method. Mon. Weather Rev. 125(12), 3297–3319 (1997)
Tribbia, J., Baumhefner, D.: Scale interactions and atmospheric predictability: an updated perspective. Mon. Weather Rev. 132(3), 703–713 (2004)
Vallis, G.K.: Atmospheric and Oceanic Fluid Dynamics. Cambridge University Press, Cambridge (2017)
Vidard, A., Anderson, D.L., Balmaseda, M.: Impact of ocean observation systems on ocean analysis and seasonal forecasts. Mon. Weather Rev. 135(2), 409–429 (2007)
Wang, Z., Akhtar, I., Borggaard, J., Iliescu, T.: Proper orthogonal decomposition closure models for turbulent flows: a numerical comparison. Comput. Methods Appl. Mech. Eng. 237, 10–26 (2012)
Weigel, A.P., Liniger, M.A., Appenzeller, C.: The discrete brier and ranked probability skill scores. Mon. Weather Rev. 135(1), 118–124 (2007)
Wiin-Nielsen, A.: Steady states and stability properties of a low-order barotropic system with forcing and dissipation. Tellus 31(5), 375–386 (1979)
Xie, X., Mohebujjaman, M., Rebholz, L.G., Iliescu, T.: Data-driven filtered reduced order modeling of fluid flows. SIAM J. Sci. Comput. 40(3), B834–B857 (2018)
Zhang, C., Mapes, B.E., Soden, B.J.: Bimodality in tropical water vapour. Quart. J. R. Meteorol. Soc. A J. Atmo. Sci. Appl. Meteorol. Phys. Oceanogr. 129(594), 2847–2866 (2003)
Zhang, F., Sun, Y.Q., Magnusson, L., Buizza, R., Lin, S.J., Chen, J.H., Emanuel, K.: What is the predictability limit of midlatitude weather? J. Atmos. Sci. 76(4), 1077–1091 (2019)
Acknowledgements
The research of N.C. is supported by the Office of Vice Chancellor for Research and Graduate Education (VCRGE) at University of Wisconsin–Madison and the Office of Naval Research (ONR) MURI N00014-19-1-2421. N.C. thanks Dr. Andrew J. Majda for useful discussions.
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Appendix
Appendix
1.1 An expectation–maximization algorithm for learning nonlinear models with partial observations
For the simplicity of discussion, define \(\widehat{{\mathbf {u}}}_{\mathbf {I}}=\{{\mathbf {u}}_{\mathbf {I}}^0, \ldots , {\mathbf {u}}_{\mathbf {I}}^j,\ldots , {\mathbf {u}}_{\mathbf {I}}^J\}\) and \(\widehat{{\mathbf {u}}}_\mathbf {II} = \{{\mathbf {u}}_\mathbf {II}^0, \ldots , {\mathbf {u}}_\mathbf {II}^j,\ldots , {\mathbf {u}}_\mathbf {II}^J\}\), where \({\mathbf {u}}_{\mathbf {I}}^j := {\mathbf {u}}_{\mathbf {I}}(t_j)\) and \({\mathbf {u}}_\mathbf {II}^j={\mathbf {u}}_\mathbf {II}(t_j)\). In other words, the values of \({\mathbf {u}}_{\mathbf {I}}\) and \({\mathbf {u}}_\mathbf {II}\) are taken at discrete points in time \({\mathbf {u}}_{\mathbf {I}}(t_j)\) and \({\mathbf {u}}_\mathbf {II}(t_j)\), for \(j = 0,1,\ldots ,J\), where \(T=J\varDelta {t}\) is the total length of the time series and \(\varDelta {t}\ll 1\). This can be achieved by applying an Euler–Maruyama scheme [33, 54] to the continuous system and discretizing the observational data as well.
Given an ansatz of the conditional Gaussian nonlinear model (6) with observed variables \({\mathbf {u}}_{\mathbf {I}}\) and unobserved variables \({\mathbf {u}}_\mathbf {II}\), the goal here is to maximize the objective function, which is the log likelihood,
where \(\varvec{\theta }\) is the collection of model parameters.
Using any distribution \(Q(\widehat{{\mathbf {u}}}_\mathbf {II})\) over the hidden variables, a lower bound on the likelihood \({\mathcal {L}}\) can be obtained in the following way [38];
where the negative value of \(\int _{\widehat{{\mathbf {u}}}_\mathbf {II}} Q(\widehat{{\mathbf {u}}}_\mathbf {II}) \log p(\widehat{{\mathbf {u}}}_{\mathbf {I}},\widehat{{\mathbf {u}}}_\mathbf {II}|\varvec{\theta }){\, \mathrm d}\widehat{{\mathbf {u}}}_\mathbf {II}\) is the so-called free energy, while \(-\int _{\widehat{{\mathbf {u}}}_\mathbf {II}} Q(\widehat{{\mathbf {u}}}_\mathbf {II}) \log Q(\widehat{{\mathbf {u}}}_\mathbf {II}){\, \mathrm d}\widehat{{\mathbf {u}}}_\mathbf {II}\) is the entropy. Therefore, based on the fact \({\mathcal {F}}(Q,\varvec{\theta })\le {\mathcal {L}}(\varvec{\theta })\), it is clear that maximizing the log likelihood is equivalent to maximizing \({\mathcal {F}}\) alternatively with respect to the distribution Q and the parameters \(\varvec{\theta }\). This can be achieved by the expectation–maximization (EM) algorithm [29, 99, 100],
The maximization in the E-Step is reached when Q is exactly the conditional distribution of \(\widehat{{\mathbf {u}}}_\mathbf {II}\) corresponding to the smoother estimates, that is,
In such a situation, the bound in (58) becomes an equality \({\mathcal {F}}(Q,\varvec{\theta })={\mathcal {L}}(\varvec{\theta })\). Note that the conditional distribution in the E-Step is very difficult to solve for general nonlinear systems. Various numerical methods and approximations are often used [37, 38], which however may suffer from both the approximation errors and the curse of dimensionality. Nevertheless, for the conditional Gaussian systems, the distribution \(p(\widehat{{\mathbf {u}}}_\mathbf {II}|\widehat{{\mathbf {u}}}_{\mathbf {I}},\varvec{\theta }_k)\) is given by the closed analytic formulae of the nonlinear smoother in Theorem 2, which greatly facilitates the application of the EM algorithm to many nonlinear models.
On the other hand, since the entropy (the second term on the right hand side of (58)) does not depend on \(\varvec{\theta }\), the maximum in the M-Step is obtained by maximizing the negative of the free energy
1.2 Parameter estimation of fully observed systems
This appendix provides more details of Step 4 of Sect. 5.1. Now assume a sampled trajectory of the unobserved variables \({\mathbf {u}}_\mathbf {II}\) is available. Assume after certain combination, the parameters only appear as prefactor coefficients in front of the nonlinear terms of the system. Therefore, the equation of \({\mathbf {u}}_\mathbf {II}\) can be rewritten as
where \({\mathbf {M}}({\mathbf {u}}_{\mathbf {I}},{\mathbf {u}}_\mathbf {II})\) contains all the nonlinear functions that depend on \({\mathbf {u}}_{\mathbf {I}}\) and conditionally linear on \({\mathbf {u}}_\mathbf {II}\) as in the original equation. The noise coefficients are provided by the EM algorithm and are not updated here. The collection of the parameters \(\varvec{\theta }\) can be estimated via a least squares estimator,
where \(t_j\) represents discrete time instants.
Rights and permissions
About this article
Cite this article
Chen, N. Improving the prediction of complex nonlinear turbulent dynamical systems using nonlinear filter, smoother and backward sampling techniques. Res Math Sci 7, 18 (2020). https://doi.org/10.1007/s40687-020-00216-5
Received:
Accepted:
Published:
DOI: https://doi.org/10.1007/s40687-020-00216-5