BfastDec: BFAST decomposition

In ndvits: NDVI Time series extraction and analysis

Description

Breaks for Additive Seasonal and Trend

Usage

BfastDec(TS, Ystart, period, param, outfile = FALSE, ...)

Arguments

TS	matrix or data.frame containing the time series (one row per time series).
Ystart	starting year of the analysis (in four-digit format).
period	number of observations per year. For VGT's dataset : period=36, GIMMS's dataset: period=24.
param	list of parameters for Bfast decomposition $season : "harmonic" or "dummy" By default, param$season = "harmonic". $h By default, param$h = period * 2/(length(as.numeric(TS[1, ]))). $maxi By default, param$maxi = 10.
outfile	name of the file where the decomposition graphs are saved (extension ".pdf"). If outfile = FALSE, the graphs are shown in R. By default, outfile=FALSE.
...	further arguments sent to Bfast function.

Value

res$seas res$trend

Author(s)

Romain Frelat and Bruno Gerard

References

Verbesselt, J., Hyndman, R., Newnham, G. and Culvenor, D. 2010 Remote Sensing of Environment, Detecting trend and seasonal changes in satellite image time series, 114, 106–115

Verbesselt, J., Hyndman, R., Zeileis, A. and Culvenor, D. 2010 Remote Sensing of Environment, Phenological change detection while accounting for abrupt and gradual trends in satellite image time series, 114, 2970–2980

See Also

STLperArea

Examples

data(SLPSAs_ts)

#Be carefull, BFAST Decomposition takes a long time
#BfastDec(SLPSAs_ts$ts, Ystart=SLPSAs_ts$Ystart, 
#    period=SLPSAs_ts$period)

ndvits documentation built on May 2, 2019, 4:47 p.m.