Latent space data assimilation by using deep learning
Authors:
Open Access
- 1 September 2021
- journal article
- research article
- Published by Wiley in Quarterly Journal of the Royal Meteorological Society
- Vol. 147 (740) , 3759-3777
Abstract
Performing data assimilation (DA) at low cost is of prime concern in Earth system modeling, particularly in the era of Big Data, where huge quantities of observations are available. Capitalizing on the ability of neural network techniques to approximate the solution of partial differential equations (PDEs), we incorporate deep learning (DL) methods into a DA framework. More precisely, we exploit the latent structure provided by autoencoders (AEs) to design an ensemble transform Kalman filter with model error (ETKF‐Q) in the latent space. Model dynamics are also propagated within the latent space via a surrogate neural network. This novel ETKF‐Q‐Latent (ETKF‐Q‐L) algorithm is tested on a tailored instructional version of Lorenz 96 equations, named the augmented Lorenz 96 system, which possesses a latent structure that accurately represents the observed dynamics. Numerical experiments based on this particular system evidence that the ETKF‐Q‐L approach both reduces the computational cost and provides better accuracy than state‐of‐the‐art algorithms such as the ETKF‐Q.Keywords
All Related Versions
This publication has 38 references indexed in Scilit:
- An iterative ensemble Kalman smootherQuarterly Journal of the Royal Meteorological Society, 2013
- Strong and weak constraint variational assimilations for reduced order fluid flow modelingJournal of Computational Physics, 2012
- On the Kalman Filter error covariance collapse into the unstable subspaceNonlinear Processes in Geophysics, 2011
- Four‐dimensional variational assimilation in the unstable subspace and the optimal subspace dimensionQuarterly Journal of the Royal Meteorological Society, 2010
- A review of forecast error covariance statistics in atmospheric variational data assimilation. I: Characteristics and measurements of forecast error covariancesQuarterly Journal of the Royal Meteorological Society, 2008
- Controlling instabilities along a 3DVar analysis cycle by assimilating in the unstable subspace: a comparison with the EnKFNonlinear Processes in Geophysics, 2008
- A reduced‐order approach to four‐dimensional variational data assimilation using proper orthogonal decompositionInternational Journal for Numerical Methods in Fluids, 2006
- Detecting unstable structures and controlling error growth by assimilation of standard and adaptive observations in a primitive equation ocean modelNonlinear Processes in Geophysics, 2006
- Wavelet transform adapted to an approximate Kalman filter systemApplied Numerical Mathematics, 2000
- A singular evolutive extended Kalman filter for data assimilation in oceanographyJournal of Marine Systems, 1998