PCAnEn - hindcasting with analogue ensembles of principal components

Balsa, Carlos; Breve, Murilo Montanini; André, Baptiste; Rodrigues, Carlos Veiga; Rufino, José

http://hdl.handle.net/10198/29571

Use this identifier to reference this record.

Name:	Description:	Size:	Format:
Artigo_PCAnEn_CSEI22.pdf		1.01 MB	Adobe PDF	Download

Send Feedback

Authors

Balsa, Carlos

Breve, Murilo Montanini

André, Baptiste

Rodrigues, Carlos Veiga

Rufino, José

Abstract(s)

The focus of this study is the reconstruction of missing meteorological data at a station based on data from neighboring stations. To that end, the Principal Components Analysis (PCA) method was applied to the Analogue Ensemble (AnEn) method to reduce the data dimensionality. The proposed technique is greatly influenced by the choice of stations according to proximity and correlation to the predicted one. PCA associated with AnEn decreased the errors in the prediction of some meteorological variables by 30% and, at the same time, decreased the prediction time by 48%. It was also verified that our implementation of this methodology in MATLAB is around two times faster than in R.

Keywords

Hindcasting Analogue ensembles Principal component analysis Time series R MATLAB

URI

http://hdl.handle.net/10198/29571

Citation

Balsa, Carlos; Breve, Murilo Montanini; André, Baptiste; Rodrigues, Carlos Veiga; Rufino, José (2023). PCAnEn - hindcasting with analogue ensembles of principal components. In International Conference on Computer Science, Electronics, and Industrial Engineering (CSEI) 2022. ISSN 2367-3370. 678, p. 169-183