Titelangaben
Ruckstuhl, Yvonne ; Janjić, Tijana ; Rasp, Stephan Rasp:
Training a convolutional neural network to conserve mass in data assimilation.
In: Nonlinear processes in geophysics. 28 (2021) 1.
- S. 111-119.
ISSN 1607-7946 ; 1023-5809
Volltext
Link zum Volltext (externe URL): https://doi.org/10.5194/npg-28-111-2021 |
Kurzfassung/Abstract
In previous work, it was shown that the preservation of physical properties in the data assimilation framework can significantly reduce forecast errors. Proposed data assimilation methods, such as the quadratic programming ensemble (QPEns) that can impose such constraints on the calculation of the analysis, are computationally more expensive, severely limiting their application to high-dimensional prediction systems as found in Earth sciences. We, therefore, propose using a convolutional neural network (CNN) trained on the difference between the analysis produced by a standard ensemble Kalman filter (EnKF) and the QPEns to correct any violations of imposed constraints. In this paper, we focus on the conservation of mass and show that, in an idealised set-up, the hybrid of a CNN and the EnKF is capable of reducing analysis and background errors to the same level as the QPEns.
Weitere Angaben
Publikationsform: | Artikel |
---|---|
Sprache des Eintrags: | Englisch |
Institutionen der Universität: | Mathematisch-Geographische Fakultät > Mathematik > Heisenberg Professur für Datenassimilation |
DOI / URN / ID: | 10.5194/npg-28-111-2021 |
Open Access: Freie Zugänglichkeit des Volltexts?: | Ja |
Peer-Review-Journal: | Ja |
Verlag: | European Geophysical Society |
Die Zeitschrift ist nachgewiesen in: | |
Titel an der KU entstanden: | Nein |
KU.edoc-ID: | 29077 |
Letzte Änderung: 31. Aug 2023 09:21
URL zu dieser Anzeige: https://edoc.ku.de/id/eprint/29077/