Suche nach Personen

plus im Publikationsserver
plus bei BASE
plus bei Google Scholar

Daten exportieren

 

Training a convolutional neural network to conserve mass in data assimilation

Titelangaben

Verfügbarkeit überprüfen

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

Open Access
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
Mathematisch-Geographische Fakultät > Mathematik > Mathematisches Institut für Maschinelles Lernen und Data Science (MIDS)
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
Eingestellt am: 07. Dez 2021 10:51
Letzte Änderung: 17. Sep 2024 15:46
URL zu dieser Anzeige: https://edoc.ku.de/id/eprint/29077/
AnalyticsGoogle Scholar