Missing values are a common concern in spatiotemporal data sets. During recent years a great number of methods have been developed for gap filling. One of the emerging approaches is based on the Empirical Orthogonal Function (EOF) methodology, applied mainly on raw and univariate data sets presenting irregular missing patterns. In this paper EOF is carried out on a multivariate space-time data set, related to concentrations of pollutants recorded at different sites, after denoising raw data by FDA approach. Some performance indicators are computed on simulated incomplete data sets with also long gaps in order to show that the EOF reconstruction appears to be an improved procedure especially when long gap sequences occur.
Ruggieri, M., Di Salvo, F., Plaia, A., Agrò, G. (2010). EOFs for gap filling in multivariate air quality data: a FDA approach. In Proceedings of COMPSTAT 2010 (pp.1557-1564). Heidelberg : Physica-Verlag.
EOFs for gap filling in multivariate air quality data: a FDA approach
RUGGIERI, Mariantonietta;DI SALVO, Francesca;PLAIA, Antonella;AGRO', Gianna
2010-01-01
Abstract
Missing values are a common concern in spatiotemporal data sets. During recent years a great number of methods have been developed for gap filling. One of the emerging approaches is based on the Empirical Orthogonal Function (EOF) methodology, applied mainly on raw and univariate data sets presenting irregular missing patterns. In this paper EOF is carried out on a multivariate space-time data set, related to concentrations of pollutants recorded at different sites, after denoising raw data by FDA approach. Some performance indicators are computed on simulated incomplete data sets with also long gaps in order to show that the EOF reconstruction appears to be an improved procedure especially when long gap sequences occur.File | Dimensione | Formato | |
---|---|---|---|
paper99.pdf
Solo gestori archvio
Descrizione: Articolo
Dimensione
158.45 kB
Formato
Adobe PDF
|
158.45 kB | Adobe PDF | Visualizza/Apri Richiedi una copia |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.