spatialEco (version 1.3-0)

raster.change: Raster change between two nominal rasters

Description

Compares two categorical rasters with a variety of statistical options

Usage

raster.change(
  x,
  y,
  d = c(3, 3),
  stat = c("kappa", "wkappa", "t.test", "cor", "entropy", "cross-entropy", "divergence"),
  w = NULL,
  out.raster = NULL,
  mask = FALSE,
  force.memory = FALSE
)

Arguments

x

First raster for comparison, rasterLayer class object

y

Second raster for comparison, rasterLayer class object

d

Rectangular window size, must be odd but not necessarily square

stat

Statistic to use in comparison, please see details for options.

w

Weights if stat="kappa", must represent same classes as input rasters

out.raster

Optional output raster

mask

(FALSE/TRUE) mask output to original rasters

force.memory

(FALSE/TRUE) Force in memory processing, may fail with insufficient RAM

Value

A raster layer or stack object one of the following layers:

• kappa Kappa or Weighted Kappa statistic (if stat = "kappa")

• correlation Paired t.test statistic (if stat = "cor")

• entropy Delta entropy (if stat = "entropy")

• divergence Kullback-Leibler divergence (if stat = "divergence")

• cross.entropy Cross-entropy (if stat = "cross.entropy")

• t.test Paired t.test statistic (if stat = "t.test")

• p.value p-value of the paired t.test statistic (if stat = "t.test")

References

Cohen, J. (1960). A coefficient of agreement for nominal scales. Educational and Psychological Measurement, 20:37-46

McHugh M.L. (2012) Interrater reliability: the kappa statistic. Biochemia medica, 22(3):276<U+2013>282.

Kullback, S., R.A. Leibler (1951). On information and sufficiency. Annals of Mathematical Statistics. 22(1):79<U+2013>86

Examples

# NOT RUN {
 library(sp)
 library(raster)
 data(meuse.grid)
 r1 <- sp::SpatialPixelsDataFrame(points = meuse.grid[c("x", "y")], 
                                  data = meuse.grid)
r1 <- raster(r1)
  na.idx <- which(!is.na(r1[]))
  r1[na.idx] <- round(runif(length(na.idx), 1,5),0)
 r2 <- sp::SpatialPixelsDataFrame(points = meuse.grid[c("x", "y")], 
                                  data = meuse.grid) 
r2 <- raster(r2)
  r2[na.idx] <- round(runif(length(na.idx), 1,5),0)
  
s = 11    
 ( r.kappa <- raster.change(r1, r2, d = s, mask = TRUE) )   
 ( r.ttest <- raster.change(r1, r2, d = s, stat="t.test", mask = TRUE) )
 ( r.ent <- raster.change(r1, r2, d = s, stat="entropy", mask = TRUE) )   
 ( r.cor <- raster.change(r1, r2, d = s, stat="cor", mask = TRUE) )
 ( r.ce <- raster.change(r1, r2, d = s, stat = "cross-entropy", mask = TRUE) )
 ( r.kl <- raster.change(r1, r2, d = s, stat = "divergence", mask = TRUE) )	
     
 par(mfrow=c(3,2))
   plot(r.kappa, main="Kappa")
   plot(r.ttest[[1]], main="Paired t-test")
   plot(r.ent, main="Delta Entropy")
   plot(r.cor, main="Rank Correlation")
   plot(r.kl, main="Kullback-Leibler")
   plot(r.ce, main="cross-entropy")

# }
# NOT RUN {
# }