| TSGFlinear {greenbrown} | R Documentation |
This function fills gaps in a time series by using linear interpolation na.approx and smoothes the time series by using running median window of size 3 runmed
TSGFlinear(Yt, interpolate = FALSE, ...)
Yt |
univariate time series of class |
interpolate |
Should the smoothed and gap filled time series be interpolated to daily values by using |
... |
further arguments (currently not used) |
The function returns a gap-filled and smoothed version of the time series.
Matthias Forkel <matthias.forkel@geo.tuwien.ac.at> [aut, cre]
# load a time series of NDVI (normalized difference vegetation index)
data(ndvi)
plot(ndvi)
# introduce random gaps
gaps <- ndvi
gaps[runif(100, 1, length(ndvi))] <- NA
plot(gaps)
# do smoothing and gap filling
tsgf <- TSGFlinear(gaps)
plot(gaps)
lines(tsgf, col="red")
# compare original data with gap-filled data
plot(ndvi[is.na(gaps)], tsgf[is.na(gaps)], xlab="original", ylab="gap filled")
abline(0,1)
r <- cor(ndvi[is.na(gaps)], tsgf[is.na(gaps)])
legend("topleft", paste("Cor =", round(r, 3)))