smooth.time.series {spatialEco}

Smooth Raster Time-series

Description

Smooths pixel-level data in raster time-series and can impute missing (NA) values.

Usage

smooth.time.series(x, f = 0.8, smooth.data = FALSE, ...)

Arguments

x

A terra SpatRaster with > 8 layers

f

Smoothing parameter (see loess span argument)

smooth.data

(FALSE/TRUE) Smooth all of the data or just impute NA values

...

Additional arguments passed to terra::app (for writing results to disk)

Details

This function uses a LOESS regression to smooth the time-series. If the data is smoothed, (using the smooth.data = TRUE argument) it will be entirely replaced by a loess estimate of the time-series (estimated distribution at the pixel-level). Alternately, with smooth.data = FALSE, the function can be used to impute missing pixel data (NA) in raster time-series (stacks/bricks). The results can dramatically be effected by the choice of the smoothing parameter (f) so caution is warranted and the effect of this parameter tested.

Value

A terra SpatRaster containing imputed or smoothed data.

Author(s)

Jeffrey S. Evans <[e-mail]>

See Also

loess for details on the loess regression

app for details on additional (...) arguments

impute.loess for details on imputation model

Examples

library(terra)
  random.raster <- function(rows=50, cols=50, l=20, min=0, max=1){ 
    do.call(c, replicate(l, rast(matrix(runif(rows * cols, min, max), 
	        rows , cols))))
  }
r <- random.raster()

#### Smooth time-series using raster stack/brick 
r.smooth <- smooth.time.series(r, f = 0.4, smooth.data = TRUE)  

# extract pixel 100 for plotting
y <- as.numeric(r[100])
ys <- as.numeric(r.smooth[100])

# plot results	
plot(y, type="l")
  lines(ys, col="red")
    legend("bottomright", legend=c("original","smoothed"),
         lty=c(1,1), col=c("black","red"))