Weather regime prediction using statistical learning

Abstract : Two novel statistical methods are applied to the prediction of transitions between weather regimes. The methods are tested using a long, 6000-day simulation of a three-layer, quasigeostrophic (QG3) model on the sphere at T21 resolution. The two methods are the k nearest neighbor classifier and the random forest method. Both methods are widely used in statistical classification and machine learning; they are applied here to forecast the break of a regime and subsequent onset of another one. The QG3 model has been previously shown to possess realistic weather regimes in its northern hemisphere and preferred transitions between these have been determined. The two methods are applied to the three more robust transitions; they both demonstrate a skill of 35%-40% better than random and are thus encouraging for use on real data. Moreover, the random forest method allows one, while keeping the overall skill unchanged, to efficiently adjust the ratio of correctly predicted transitions to false alarms. A long-standing conjecture has associated regime breaks and preferred transitions with distinct directions in the reduced model phase space spanned by a few leading empirical orthogonal functions of its variability. Sensitivity studies for several predictors confirm the crucial influence of the exit angle on a preferred transition path. The present results thus support the paradigm of multiple weather regimes and their association with unstable fixed points of atmospheric dynamics. © 2007 American Meteorological Society.
Type de document :
Article dans une revue
Journal of the Atmospheric Sciences, American Meteorological Society, 2007, 64 (5), pp.1619-1635. 〈10.1175/jas3918.1〉
Liste complète des métadonnées

Littérature citée [28 références]  Voir  Masquer  Télécharger

https://hal-polytechnique.archives-ouvertes.fr/hal-01023347
Contributeur : Denis Roura <>
Soumis le : dimanche 20 juillet 2014 - 18:54:44
Dernière modification le : mercredi 25 avril 2018 - 10:45:03
Document(s) archivé(s) le : jeudi 20 novembre 2014 - 18:16:20

Fichier

jas39182E1.pdf
Fichiers éditeurs autorisés sur une archive ouverte

Identifiants

Collections

Citation

Axel Deloncle, R. Berk, F. D'Andrea, M. Ghil. Weather regime prediction using statistical learning. Journal of the Atmospheric Sciences, American Meteorological Society, 2007, 64 (5), pp.1619-1635. 〈10.1175/jas3918.1〉. 〈hal-01023347〉

Partager

Métriques

Consultations de la notice

348

Téléchargements de fichiers

151