3D-Var data assimilation using a variational autoencoder

Melinc, Boštjan (author), Zaplotnik, Žiga (author)

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 autodifferentiable, simplifying the computation of the cost-function gradient necessary for efficient minimisation. We demonstrate that the background-error covariance (B) matrix measured and represented in the latent space is quasidiagonal. 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 B matrix describes both tropical and extratropical background-error covariances simultaneously.

• Language: English
• Keywords: meteorology, data assimilation, machine learning, neural networks, variational autoencoder, 3D-Var, analysis increments, background errors
• Work type: Article
• Typology: 1.01 - Original Scientific Article
• Organization: FMF - Faculty of Mathematics and Physics
• Publication status: Published
• Publication version: Version of Record
• Year: 2024
• Number of pages: Str. 2273–2295
• Numbering: Vol. 150, iss. 761, pt. B
• PID: 20.500.12556/RUL-158318
• UDC: 551.5
• ISSN on article: 0035-9009
• DOI: 10.1002/qj.4708
• COBISS.SI-ID: 194564099
• Publication date in RUL: 05.06.2024

Record is a part of a journal

• Title: Quarterly journal of the Royal Meteorological Society
• Shortened title: Q. j. R. Meteorol. Soc.
• Publisher: Wiley, Royal Meteorological Society
• ISSN: 0035-9009
• COBISS.SI-ID: 26227200

Licences

• License: CC BY 4.0, Creative Commons Attribution 4.0 International
• Link: http://creativecommons.org/licenses/by/4.0/
• Description: This is the standard Creative Commons license that gives others maximum freedom to do what they want with the work as long as they credit the author.

Secondary language

• Language: Slovenian
• Keywords: meteorologija, asimilacija meritev, strojno učenje, nevronske mreže, variacijski avtokodirnik, 3D-Var