Suche nach Personen

plus im Publikationsserver
plus bei BASE
plus bei Google Scholar

Daten exportieren

 

Combining data assimilation and machine learning to estimate parameters of a convective-scale model

Titelangaben

Verfügbarkeit überprüfen

Legler, Stefanie ; Janjić, Tijana:
Combining data assimilation and machine learning to estimate parameters of a convective-scale model.
In: Quarterly journal of the Royal Meteorological Society. (20. Dezember 2021). - 15 S.
ISSN 1477-870x ; 0035-9009

Volltext

Open Access
Volltext Link zum Volltext (externe URL):
https://doi.org/10.1002/qj.4235

Kurzfassung/Abstract

Errors in the representation of clouds in convection-permitting numerical weather prediction models can be introduced by different sources. These can be the forcing and boundary conditions, the representation of orography, the accuracy of the numerical schemes determining the evolution of humidity and temperature, but large contributions are due to the parametrization of microphysics and the parametrization of processes in the surface and boundary layers. These schemes typically contain several tunable parameters that are either not physical or only crudely known, leading to model errors. Traditionally, the numerical values of these model parameters are chosen by manual model tuning. More objectively, they can be estimated from observations by the augmented state approach during the data assimilation. Alternatively, in this work, we look at the problem of parameter estimation through an artificial intelligence lens by training two types of artificial neural network (ANN) to estimate several parameters of the one-dimensional modified shallow-water model as a function of the observations or analysis of the atmospheric state. Through perfect model experiments we show that Bayesian neural networks (BNNs) and Bayesian approximations of point estimate neural networks (NNs) are able to estimate model parameters and their relevant statistics. The estimation of parameters combined with data assimilation for the state decreases the initial state errors even when assimilating sparse and noisy observations. The sensitivity to the number of ensemble members, observation coverage and neural network size is shown. Additionally, we use the method of layer-wise relevance propagation to gain insight into how the ANNs are learning and discover that they naturally select only a few grid points that are subject to strong winds and rain to make their predictions of chosen parameters.

Weitere Angaben

Publikationsform:Artikel
Schlagwörter:Bayesian neural network, convective-scale data assimilation, EnKF, layer-wise relevance propagation, parameter estimation
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:10.1002/qj.4235
Open Access: Freie Zugänglichkeit des Volltexts?:Ja
Peer-Review-Journal:Ja
Verlag:Wiley
Die Zeitschrift ist nachgewiesen in:
Titel an der KU entstanden:Nein
KU.edoc-ID:29668
Eingestellt am: 14. Feb 2022 10:45
Letzte Änderung: 16. Sep 2024 15:53
URL zu dieser Anzeige: https://edoc.ku.de/id/eprint/29668/
AnalyticsGoogle Scholar