Buchumschlag

Multivariate probabilistic forecasting using ensemble Bayesian model averaging and copulas

We propose a method for post-processing an ensemble of multivariate forecasts in order to obtain a joint predictive distribution of weather. Our method utilizes existing univariate post-processing techniques, in this case ensemble Bayesian model averaging (BMA), to obtain estimated marginal distribu...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Möller, Annette (VerfasserIn) , Lenkoski, Alex (VerfasserIn) , Thorarinsdottir, Thordis (VerfasserIn)
Dokumenttyp: Article (Journal)
Sprache:Englisch
Veröffentlicht: 2013
In: Quarterly journal of the Royal Meteorological Society
Year: 2012, Jahrgang: 139, Heft: 673, Pages: 982-991
ISSN:1477-870X
DOI:https://doi.org/10.1002/qj.2009
Online-Zugang:Verlag, lizenzpflichtig, Volltext: https://doi.org/https://doi.org/10.1002/qj.2009
Verlag, lizenzpflichtig, Volltext: https://rmets.onlinelibrary.wiley.com/doi/abs/10.1002/qj.2009
Volltext
Verfasserangaben:Annette Möller, Alex Lenkoski and Thordis L. Thorarinsdottir
Beschreibung
Zusammenfassung:We propose a method for post-processing an ensemble of multivariate forecasts in order to obtain a joint predictive distribution of weather. Our method utilizes existing univariate post-processing techniques, in this case ensemble Bayesian model averaging (BMA), to obtain estimated marginal distributions. However, implementing these methods individually offers no information regarding the joint distribution. To correct this, we propose the use of a Gaussian copula, which offers a simple procedure for recovering the dependence that is lost in the estimation of the ensemble BMA marginals. Our method is applied to 48 h forecasts of a set of five weather quantities using the eight-member University of Washington mesoscale ensemble. We show that our method recovers many well-understood dependencies between weather quantities and subsequently improves calibration and sharpness over both the raw ensemble and a method which does not incorporate joint distributional information. Copyright © 2012 Royal Meteorological Society
Beschreibung:Published online in Wiley online library 17 September 2012
Gesehen am 25.05.2021
Beschreibung:Online Resource
ISSN:1477-870X
DOI:https://doi.org/10.1002/qj.2009

Ähnliche Einträge