predict: EOT based spatial prediction

In environmentalinformatics-marburg/remote: Empirical Orthogonal Teleconnections in R

EOT based spatial prediction

Description

Make spatial predictions using the fitted model returned by eot. A (user-defined) set of n modes will be used to model the outcome using the identified link functions of the respective modes which are added together to produce the final prediction.

Usage

## S4 method for signature 'EotStack'
predict(object, newdata, n = 1, cores = 1L, filename = "", ...)

## S4 method for signature 'EotMode'
predict(object, newdata, n = 1, cores = 1L, filename = "", ...)

Arguments

object	an Eot* object
newdata	the data to be used as predictor
n	the number of modes to be used for the prediction. See nXplain for calculating the number of modes based on their explanatory power.
cores	integer. Number of cores for parallel processing.
filename	character, output filenames (optional). If specified, this must be of the same length as nlayers(newdata).
...	further arguments passed to calc, and hence, writeRaster.

Value

a RasterStack of nlayers(newdata)

See Also

calc, writeRaster.

Examples

### not very useful, but highlights the workflow
data(pacificSST)
data(australiaGPCP)

## train data using eot()
train <- eot(x = pacificSST[[1:10]],
             y = australiaGPCP[[1:10]],
             n = 1)

## predict using identified model
pred <- predict(train,
                newdata = pacificSST[[11:20]],
                n = 1)

## compare results
opar <- par(mfrow = c(1,2))
plot(australiaGPCP[[13]], main = "original", zlim = c(0, 10))
plot(pred[[3]], main = "predicted", zlim = c(0, 10))
par(opar)

environmentalinformatics-marburg/remote documentation built on July 5, 2023, 4:36 p.m.