Premium
Singular spectrum analysis for time series with missing data
Author(s) -
Schoellhamer David H.
Publication year - 2001
Publication title -
geophysical research letters
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 2.007
H-Index - 273
eISSN - 1944-8007
pISSN - 0094-8276
DOI - 10.1029/2000gl012698
Subject(s) - singular spectrum analysis , missing data , series (stratigraphy) , time series , multivariate statistics , filter (signal processing) , computer science , data mining , remote sensing , geology , algorithm , singular value decomposition , machine learning , paleontology , computer vision
Geophysical time series often contain missing data, which prevents analysis with many signal processing and multivariate tools. A modification of singular spectrum analysis for time series with missing data is developed and successfully tested with synthetic and actual incomplete time series of suspended‐sediment concentration from San Francisco Bay. This method also can be used to low pass filter incomplete time series.