reclass.nbs: Reclassify neighbors

In scapesClassification: User-Defined Classification of Raster Surfaces

Reclassify neighbors

Description

Evaluate if members of two classes are contiguous and, if they are, one of them is reclassified.

Usage

reclass.nbs(
  attTbl,
  ngbList,
  rNumb = FALSE,
  classVector,
  nbs_of,
  class,
  reclass,
  reclass_all = TRUE
)

Arguments

attTbl	data.frame, the attribute table returned by the function attTbl.
ngbList	list, the list of neighborhoods returned by the function ngbList.
rNumb	logic, the neighborhoods of the argument ngbList are identified by cell numbers (rNumb=FALSE) or by row numbers (rNumb=TRUE) (see ngbList). It is advised to use row numbers for large rasters.
classVector	numeric vector, defines the cells in the attribute table that have already been classified. See conditions for more information about class vectors.
nbs_of	numeric or numeric vector, indicates the class(es) of focal and anchor cells.
class	numeric or numeric vector, cells of classes class adjacent to cells belonging to one of the classes of nbs_of are reclassified as indicated by the argument reclass.
reclass	numeric, the classification number to assign to all cells that meet the function conditions.
reclass_all	logic, all cells of class class are also reclassified if they are connected to a reclassified cell.

Details

• The function evaluates if a cell of class class is adjacent to a cell of class nbs_of and, if it is, it is reclassifies as indicated by the argument reclass.

• If the argument reclass_all = TRUE, all cells of class class are also reclassified if they are connected to a reclassified cell.

Value

Update classVector with the new cells that were classified by the function. See conditions for more information about class vectors.

See Also

attTbl(), ngbList(), cond.reclass(), classify.all()

Examples

library(scapesClassification)
library(terra)

# LOAD THE DUMMY RASTER
r <- list.files(system.file("extdata", package = "scapesClassification"),
                pattern = "dummy_raster\\.tif", full.names = TRUE)
r <- terra::rast(r)

# COMPUTE THE ATTRIBUTE TABLE
at <- attTbl(r, "dummy_var")

# COMPUTE THE LIST OF NEIGBORHOODS
nbs <- ngbList(r)

################################################################################
# RECLASS.NBS
################################################################################

# Compute an inital class vector with `cond.4.all`
cv <- cond.4.all(attTbl = at, cond = "dummy_var > 5", class = 1)

# Update the class vector with a second class
cv <- cond.4.all(attTbl = at, cond = "dummy_var >= 2", class = 2,
                 classVector = cv)


# Reclassify cells of class 2 adjacent to cells of class 1

# reclass_all = FALSE
rc1 <- reclass.nbs(attTbl = at, ngbList = nbs,

                   # CLASS VECTOR `cv`
                   classVector = cv,

                   # CELLS OF CLASS...
                   class = 2,

                   # ...ADJACENT TO CELLS OF ANOTHER CLASS...
                   nbs_of = 1,

                   # ...WILL BE RECLASSIFIED...
                   reclass = 3,

                   # NO MORE RECLASSIFICATIONS
                   reclass_all = FALSE)

# reclass_all = TRUE
rc2 <- reclass.nbs(attTbl = at, ngbList = nbs,

                   # CLASS VECTOR `cv`
                   classVector = cv,

                   # CELLS OF CLASS...
                   class = 2,

                   # ...ADJACENT TO CELLS OF ANOTHER CLASS...
                   nbs_of = 1,

                   # ...WILL BE RECLASSIFIED...
                   reclass = 3,

                   # ...AND SO ALL CELLS OF CLASS 1 CONNECTED TO A RECLASSIFIED CELL
                   reclass_all = TRUE)

# Convert class vectors to rasters
r_cv  <- cv.2.rast(r, at$Cell,classVector = cv, plot = FALSE)
r_rc1 <- cv.2.rast(r, at$Cell,classVector = rc1, plot = FALSE)
r_rc2 <- cv.2.rast(r, at$Cell,classVector = rc2, plot = FALSE)

################################################################################
# PLOTS
################################################################################
oldpar <- par(mfrow = c(2,2))
m = c(0.1, 3.5, 3.2, 3.5)


# 1)
plot(r_cv, type="classes", axes=FALSE, legend = FALSE, asp = NA, mar=m,
     colNA="#818792", col=c("#1088a0", "#78b2c4"))
text(r)
mtext(side=3, line=2, adj=0, cex=1, font=2, "COND.4.ALL")
mtext(side=3, line=1, adj=0, cex=0.9, "Step1: 'dummy_var > 5', class: 1")
mtext(side=3, line=0, adj=0, cex=0.9, "Step2: 'dummy_var > 3', class: 2")
legend("bottomright", ncol = 1, bg = "white", y.intersp= 1.2,
       legend = c("Class 1", "Class 2", "Unclassified cells"),
      fill = c("#1088a0", "#78b2c4", "#818792"))

# 2)
plot(r_rc1, type="classes", axes=FALSE, legend = FALSE, asp = NA, mar=m,
     colNA="#818792", col=c("#1088a0", "#78b2c4", "#cfad89"))
text(r)
mtext(side=3, line=2, adj=0, cex=1, font=2, "RECLASS.NBS")
mtext(side=3, line=1, adj=0, cex=0.9, "Reclass: class 2 adjacent to class 1")
mtext(side=3, line=0, adj=0, cex=0.9, "reclass_all = FALSE")
legend("bottomright", ncol = 1, bg = "white", y.intersp= 1.2,
       legend = c("Reclassified cells"), fill = c("#cfad89"))

# 3)
plot(r_rc2, type="classes", axes=FALSE, legend = FALSE, asp = NA, mar=m,
     colNA="#818792", col=c("#1088a0", "#78b2c4", "#cfad89"))
text(r)
mtext(side=3, line=2, adj=0, cex=1, font=2, "RECLASS.NBS")
mtext(side=3, line=1, adj=0, cex=0.9, "Reclass: class 2 adjacent to class 1")
mtext(side=3, line=0, adj=0, cex=0.9, "reclass_all = TRUE")
legend("bottomright", ncol = 1, bg = "white", y.intersp= 1.2,
       legend = c("Reclassified cells"), fill = c("#cfad89"))
par(oldpar)

scapesClassification documentation built on March 18, 2022, 6:32 p.m.