Sequential State and Variance Estimation within the Ensemble Kalman Filter

Stroud, Jonathan R.; Bengtsson, Thomas
September 2007
Monthly Weather Review;Sep2007, Vol. 135 Issue 9, p3194
Academic Journal
Kalman filter methods for real-time assimilation of observations and dynamical systems typically assume knowledge of the system parameters. However, relatively little work has been done on extending state estimation procedures to include parameter estimation. Here, in the context of the ensemble Kalman filter, a Monte Carlo–based algorithm is proposed for sequential estimation of the states and an unknown scalar observation variance. A Bayesian approach is adopted that yields analytical updating of the parameter distribution and provides samples from the posterior distribution of the states and parameters. The proposed assimilation algorithm extends standard ensemble methods, including perturbed observations, and serial and square root assimilation schemes. The method is illustrated on the Lorenz 40-variable system and is shown to be robust with system nonlinearities, sparse observation networks, and the choice of the initial parameter distribution.


Related Articles

  • Bayesian Comparison of Kalman Filters with Known Covariance Matrices. Dokoupil, Jakub; Papež, Milan; Václavek, Pavel // AIP Conference Proceedings;2015, Vol. 1648 Issue 1, p1 

    A growing-window recursive procedure for model comparison is proposed based on the Bayesian inference principle. This procedure, compared to the batch one, is capable of processing unlimited increases in the uncertainty of the initial parameter settings, which is a characteristic of Kalman type...

  • Reserve Estimation. Sutawanir; Gunawan, Agus Yodi; Permadi, Asep K.; Fitriyati, Nina // AIP Conference Proceedings;2014, Vol. 1589, p436 

    Estimation of recoverable reservoir reserve should be as accurate as possible. Detailed reservoir parameter estimation is needed to ensure good estimate. Many uncertainties exist in recovery estimation due to reservoir rock properties such as permeability and porosity. The estimate of such...

  • Stochastic Model Reconstruction From Incomplete Noisy Measurements. Luchinsky, D. G.; Smelyanskiy, V. N.; Smith, J. // AIP Conference Proceedings;2005, Vol. 800 Issue 1, p539 

    A technique of reconstruction of both unknown state and unknown vector-field of stochastic nonlinear dynamical system is introduced. It is based on the application of the path-integral theory to the full Bayesian inference and extended Kalman filter theory. We illustrate the application of this...

  • Parameter estimation using chaotic time series. Annan, J. D. // Tellus: Series A;Oct2005, Vol. 57 Issue 5, p709 

    We show how the response of a chaotic model to temporally varying external forcing can be efficiently tuned via parameter estimation using time series data, extending previous work in which an unforced climatologically steady state was used as the tuning target. Although directly fitting a long...

  • Parameter estimation in an atmospheric GCM using the Ensemble Kalman Filter. Annan, J. D.; Lunt, D. J.; Hargreaves, J. C.; Valdes, P. J.; Vannitsem, S. // Nonlinear Processes in Geophysics;2005, Vol. 12 Issue 3, p363 

    We demonstrate the application of an efficient multivariate probabilistic parameter estimation method to a spectral primitive equation atmospheric GCM. The method, which is based on the Ensemble Kalman Filter, is effective at tuning the surface air temperature climatology of the model to both...

  • Ensemble Kalman filtering with residual nudging. Luo, Xiaodong; Hoteit, Ibrahim // Tellus: Series A;2012, Vol. 64, p1 

    Covariance inflation and localisation are two important techniques that are used to improve the performance of the ensemble Kalman filter (EnKF) by (in effect) adjusting the sample covariances of the estimates in the state space. In this work, an additional auxiliary technique, called residual...

  • Ensemble data assimilation with an adjusted forecast spread. Rainwater, Sabrina; Hunt, Brian R. // Tellus: Series A;2013, Vol. 65, p1 

    Ensemble data assimilation typically evolves an ensemble of model states whose spread is intended to represent the algorithm's uncertainty about the state of the physical system that produces the data. The analysis phase treats the forecast ensemble as a random sample from a background...

  • Sequential Bayesian State and Parameter Estimation of Non Linear Stochastic Systems. Souibgui, F.; Hmida, F. Ben; Chaari, A.; Gossa, M. // International Review of Automatic Control;Sep2010, Vol. 3 Issue 5, p457 

    This paper presents the problem of Bayesian state and parameter estimation in stochastic non linear systems. However, the presence of parameters in the system equations makes their use more complex and can even impair their convergence properties. In this paper, a new formulation of Particle...

  • Time domain parameters identification of foundation-structure interaction system. Huang Yi; Liu Zeng-rong // Applied Mathematics & Mechanics;Jul2005, Vol. 26 Issue 7, p855 

    The time domain parameter identification method of the foundation-structure interaction system is presented. On the basis of building the computation mode and the motion equation of the foundation-structure interaction system, the system parameter identification method was established by using...


Read the Article


Sorry, but this item is not currently available from your library.

Try another library?
Sign out of this library

Other Topics