• Corpus ID: 211677550

A Stochastic Covariance Shrinkage Approach in Ensemble Transform Kalman Filtering

  title={A Stochastic Covariance Shrinkage Approach in Ensemble Transform Kalman Filtering},
  author={Andrey A. Popov and Adrian Sandu and Elias D. Ni{\~n}o and Geir Evensen},
Operational Ensemble Kalman Filtering (EnKF) methods rely on model-specific heuristics such as localization, which are typically implemented based on the spacial locality of the model variables. We instead propose methods that more closely depend on the dynamics of the model, by looking at locally averaged-in-time behavior. Such behavior is typically described in terms of a climatological covariance of the dynamical system. We will be utilizing this covariance as the target matrix in covariance… 
3 Citations

Figures from this paper

EnKF data-driven reduced order assimilation system
A Multifidelity Ensemble Kalman Filter with Reduced Order Control Variates
Numerical results show that the two-fidelity MFEnKF provides better analyses than existing EnKF algorithms at comparable or reduced computational costs.
A Stochastic Covariance Shrinkage Approach to Particle Rejuvenation in the Ensemble Transform Particle Filter
This work aims at improving canonical rejuvenation methodology by the introduction of additional prior information obtained from climatological samples; the dynamical particles used for importance sampling are augmented with samples obtained from stochastic covariance shrinkage.


Predictability: A problem partly solved
  • In Proc. Seminar on predictability,
  • 1996
Efficient parallel implementation of DDDAS inference using an ensemble Kalman filter with shrinkage covariance matrix estimation
The proposed implementation outperforms in terms of accuracy the well-known local ensemble transform Kalman filter (LETKF) for all the model variables.
Ensemble Kalman filter implementations based on shrinkage covariance matrix estimation
This paper develops efficient ensemble Kalman filter (EnKF) implementations based on shrinkage covariance estimation. The forecast ensemble members at each step are used to estimate the background
ODE Test Problems: a MATLAB suite of initial value problems
ODE Test Problems (OTP) is an object-oriented MATLAB package offering a broad range of initial value problems which can be used to test numerical methods such as time integration methods and data
ODE test problems
  • 2020
Data-driven correction reduced order models for the quasi-geostrophic equations: a numerical investigation
Numerical investigation of the recently introduced data-driven correction reduced order model (DDC-ROM) in the numerical simulation of the quasi-geostrophic equations shows that, for low-dimensional ROMs, both the D DC-ROM and CDDC- ROM perform better than the standard Galerkin ROM (G- ROM) and the CDDC -ROM provides the best results.
A Bayesian Approach to Multivariate Adaptive Localization in Ensemble-Based Data Assimilation with Time-Dependent Extensions
This work proposes a Bayesian approach to adaptive Schur-product localization for the DEnKF, and extends it to support multiple radii of influence, and shows that the multivariate approach has great promise on the toy problem, and that the univariate approach leads to improved filter performance for the realistic geophysical problem.
An Ensemble Kalman Filter Implementation Based on Modified Cholesky Decomposition for Inverse Covariance Matrix Estimation
The results reveal that the use of modified Cholesky for inverse covariance matrix estimation can reduce the impact of spurious correlations during the assimilation cycle, i.e., the results of the proposed method are of better quality than those obtained via the LETKF in terms of root mean square error.
Data Assimilation: Methods, Algorithms, and Applications
This book provides a framework for, and insight into, the inverse problem nature of data assimilation, emphasizing “why” and not just “how”, and provides a comprehensive guide that is accessible to nonexperts.
A parallel ensemble Kalman filter implementation based on modified Cholesky decomposition
The proposed implementation outperforms in terms of accuracy the well-known local ensemble transform Kalman filter (LETKF) for all the model variables and for the largest number of processors, is 400 times faster than the serial version of the proposed method.