Covariance regularization in inverse space
Authors:
Open Access
- 25 June 2009
- journal article
- research article
- Published by Wiley in Quarterly Journal of the Royal Meteorological Society
- Vol. 135 (642) , 1133-1156
Abstract
In data assimilation, covariance matrices are introduced in order to prescribe the weights of the initial state, model dynamics, and observation, and suitable specification of the covariances is known to be essential for obtaining sensible state estimates. The covariance matrices are specified by sample covariances and are converted according to an assumed covariance structure. Modelling of the covariance structure consists of the regularization of a sample covariance and the constraint of a dynamic relationship. Regularization is required for converting the singular sample covariance into a non‐singular sample covariance, removing spurious correlation between variables at distant points, and reducing the required number of parameters that specify the covariances. In previous studies, regularization of sample covariances has been carried out in physical (grid) space, spectral space, and wavelet space. We herein propose a method for covariance regularization in inverse space, in which we use the covariance selection model (the Gaussian graphical model). For each variable, we assume neighbouring variables, i.e. a targeted variable is directly related to its neighbours and is conditionally independent of the non‐neighbouring variables. Conditional independence is expressed by specifying zero elements in the inverse covariance matrix. The non‐zero elements are estimated numerically by the maximum likelihood using Newton's method. Appropriate neighbours can be selected with the AIC or BIC information criteria. We address some techniques for implementation when the covariance matrix has a large dimension. We present an illustrative example using a simple 3 × 3 matrix and an application to a sample covariance obtained from sea‐surface height observations. Copyright © 2009 Royal Meteorological SocietyKeywords
Funding Information
- Physical Oceanography Distributed Active Archive Center
- Japan Science Technology Agency
This publication has 56 references indexed in Scilit:
- Use of Canadian Quick covariances in the Met Office data assimilation systemQuarterly Journal of the Royal Meteorological Society, 2008
- Spatial averaging of ensemble‐based background‐error variancesQuarterly Journal of the Royal Meteorological Society, 2008
- Flow‐adaptive moderation of spurious ensemble correlations and its use in ensemble‐based data assimilationQuarterly Journal of the Royal Meteorological Society, 2007
- Spectral and spatial localization of background‐error correlations for data assimilationQuarterly Journal of the Royal Meteorological Society, 2007
- Ensemble-derived stationary and flow-dependent background-error covariances: Evaluation in a quasi-operational NWP settingQuarterly Journal of the Royal Meteorological Society, 2005
- Four-dimensional variational data assimilation: A new formulation of the background-error covariance matrix based on a potential-vorticity representationQuarterly Journal of the Royal Meteorological Society, 2003
- Assimilation of surface velocity data into a primitive equation coastal ocean modelJournal of Geophysical Research: Oceans, 2002
- Spatial regression and multiscale approximations for sequential data assimilation in ocean modelsJournal of Geophysical Research: Oceans, 1999
- Estimating the Dimension of a ModelThe Annals of Statistics, 1978
- A new look at the statistical model identificationIEEE Transactions on Automatic Control, 1974