krigeLgm: Spatial prediction, or Kriging

Description

Perform spatial prediction, producing a raster of predictions and conditional standard deviations.

Usage

krigeLgm(formula, data, grid,  covariates = NULL,
	param,  
    expPred = FALSE, nuggetInPrediction = TRUE,
    mc.cores=getOption("mc.cores", 1L))

Value

A raster is returned with the following layers:

fixed: Estimated means from the fixed effects portion of the model
random: Predicted random effect
krige.var: Conditional variance of predicted random effect (on the transformed scale if applicable)
predict: Prediction of the response, sum of fixed and random effects. If exp.pred is TRUE, gives predictions on the exponentiated scale, and half of krige.var is added prior to exponentiating
predict.log: If exp.pred=TRUE, the prediction of the logged process.
predict.boxcox: If a box cox transformation was used, the prediction of the process on the transformed scale.

If the prediction locations are different for fixed and random effects (typically coarser for the random effects), a list with two raster stacks is returned.

prediction: A raster stack as above, though the random effect prediction is resampled to the same locations as the fixed effects.
random: the predictions and conditional variance of the random effects, on the same raster as newdata

Arguments

formula: Either a model formula, or a data frame of linear covariates.
data: A SpatVector containing the data to be interpolated
grid: Either a SpatRaster , or a single integer giving the number of cells in the X direction which predictions will be made on. If the later the predictions will be a raster of square cells covering the bounding box of data.
covariates: The spatial covariates used in prediction, either a SpatRaster stack or list of rasters.
param: A vector of named model parameters, as produced by likfitLgm
expPred: Should the predictions be exponentiated, defaults to FALSE.
nuggetInPrediction: If TRUE, predict new observations by adding the nugget effect. The prediction variances will be adjusted accordingly, and the predictions on the natural scale for logged or Box Cox transformed data will be affected. Otherwise predict fitted values.
mc.cores: passed to mclapply if greater than 1.

Details

Given the model parameters and observed data, conditional means and variances of the spatial random field are computed.

Examples

Run this code

data('swissRain')
swissAltitude = unwrap(swissAltitude)
swissRain = unwrap(swissRain)
swissRain$lograin = log(swissRain$rain)
swissRain[[names(swissAltitude)]] = extract(swissAltitude, swissRain, ID=FALSE)

swissFit = likfitLgm(data=swissRain, 
			formula=lograin~ CHE_alt,
			param=c(range=46500, nugget=0.05,shape=1,  
					anisoAngleDegrees=35, anisoRatio=12),
			paramToEstimate = c("range","nugget", 
				"anisoAngleDegrees", "anisoRatio")
)
myTrend = swissFit$model$formula
myParams = swissFit$param


swissBorder = unwrap(swissBorder)

swissKrige = krigeLgm(
	data=swissRain, 
	formula = myTrend,
	covariates = swissAltitude,  
	param=myParams,
	grid = squareRaster(swissBorder, 40), expPred=TRUE)

plot(swissKrige[["predict"]], main="predicted rain")
plot(swissBorder, add=TRUE)