Detecting Climatic Signals from Ship's Datasets
Résumé
The main objective of this work is to present a new multivariate statistical method to deal with irregular sampling in ship's gridded datasets. The method may be termed weighted Empirical Orthogonal Function (EOF) analysis or weighted Singular Value Decomposition (SVD) analysis and is a generalization of the traditional EOF analysis, or more precisely, of truncated SVD analysis. This method accounts for the irregular space-time sampling of the ship-reports by the use of weights (a weight is associated with each cell-month entry of the data matrix) in approximating the data matrix by a lower rank matrix in the least squares sense. In contrast, the traditional SVD analysis assumes that all the cells have equal weights in solving the same optimization problem.
Domaines
Océan, AtmosphèreOrigine | Fichiers produits par l'(les) auteur(s) |
---|
Loading...