rsMove (version 0.2.1)

modelApply: modelApply

Description

Apply a model or an ensemble of models to raster data.

Usage

modelApply(model, img, fun = NULL)

Arguments

model

List object as provided by moveModel().

img

Object of class RasterLayer, RasterStack or RasterBrick.

fun

Function that specifies how the model should be applied.

Value

A Raster.

Details

The function uses the output of moveModel(). If this contains a list of models from multiple runs, the function creates a stack of predictions and summarizes it on a pixel-by-pixel basis using a weighted mean. The weights are defined by the average performance for presence and background samples in each iteration.

See Also

segRaster moveModel

Examples

# NOT RUN {
 
 require(raster)
 
 # read remote sensing data
 file <- list.files(system.file('extdata', '', package="rsMove"), 'tc.*tif', full.names=TRUE)
 rsStk <- stack(file)
 
 # read movement data
 moveData <- read.csv(system.file('extdata', 'konstanz_20130805-20130811.csv', package="rsMove"))
 moveData <- SpatialPointsDataFrame(moveData[,1:2], moveData, proj4string=crs(rsStk))
 
 # retrieve remote sensing data for samples
 rsQuery <- dataQuery(xy=moveData,img=rsStk, remove.dup=TRUE)
 
 # identify unique sample regions
 label <- labelSample(xy=rsQuery, rad=90, npx=1, pxr=rsStk)
 
 # select background samples
 ind <- which(label>0) # selected samples
 bSamples <- backSample(xy=moveData[ind,], rid=label[ind], img=rsStk, nb=4000, method='pca')
 
 # derive model predictions
 fun <- function(x,y) {train(x, y, method="rf", trControl=trainControl(method='oob'))}
 p.model <- moveModel(p.data=rsQuery@data, a.data=bSamples@data, label=label, fun=fun, nruns=1)

 # derive prediction from model ensemble
 fun <- function(x,y) {predict(x, y, type='prob')[[1]]$`1`}
 prob <- modelApply(p.model, rsStk, fun=fun)
 
 # see output
 plot(prob)
 
# }