3D-Var Data Assimilation using a Variational Autoencoder
arXiv:2308.16073 · doi:10.1002/qj.4708
Abstract
Data assimilation of atmospheric observations traditionally relies on variational and Kalman filter methods. Here, an alternative neural-network data assimilation (NNDA) with variational autoencoder (VAE) is proposed. The three-dimensional variational (3D-Var) data assimilation cost function is utilised to determine the analysis that optimally fuses simulated observations and the encoded short-range persistence forecast (background), accounting for their errors. The minimisation is performed in the reduced-order latent space, discovered by the VAE. The variational problem is auto-differentiable, simplifying the computation of the cost function gradient necessary for efficient minimisation. We demonstrate that the background-error covariance () matrix measured and represented in the latent space is quasi-diagonal. The background-error covariances in the grid-point space are flow-dependent, evolving seasonally and depending on the current state of the atmosphere. Data assimilation experiments with a single temperature observation in the lower troposphere indicate that the -matrix simultaneously describes both tropical and extratropical background-error covariances.
Peer-reviewed version of this paper has been published in QJRMS (https://doi.org/10.1002/qj.4708). The uploaded version in this repository is not the same as the peer-reviewed version
References in corpus (6)
- Using machine learning to correct model error in data assimilation and forecast applications
- Combining distribution-based neural networks to predict weather forecast probabilities
- A reduced-order strategy for 4D-Var data assimilation
- Attention-based Convolutional Autoencoders for 3D-Variational Data Assimilation
- Machine Learning Emulation of 3D Cloud Radiative Effects
- Combining data assimilation and machine learning to estimate parameters of a convective-scale model