sdm (version 1.1-8)

predict: sdm model prediction

Description

Make a Raster or matrix object (depending on input dataset) with predictions from one or several fitted models in sdmModels object.

Usage

# S4 method for sdmModels
predict(object, newdata, filename="", w=NULL,species=NULL
          ,method=NULL,replication=NULL,run=NULL,mean=FALSE,control=NULL,
          overwrite=TRUE,nc=1,obj.size=1, ...)

Value

a Raster object or data.frame

Arguments

object

sdmModels object

newdata

Raster* object, or data.frame

filename

character, output file name, if missing, a name starts with sdm_prediction will be generated

w

numeric, specifies which model(s) should be used if the object contains several models; with NULL all models are used

species

character, (optional), specifies which species should be used if the object contains models for multiple species; with NULL all species are used

method

character, names of fitted models, e.g., glm, brt, etc.

replication

character, specifies the names of replication method,if NULL, all available replications are considered

run

numeric, works if replication with multiple runs are used

mean

logical, works if replication with multiple runs are used to fit the models, and specifies whether a mean should be calculated over all predictions of a replication method (e.g., bootstrapping) for each modelling method.

control

not implemented yet!

overwrite

logical, whether the filename should be overwriten it it does exist

nc

number of cores for parallel running of the function

obj.size

the size of object can be kept in memory (default=1 Giga byte). Depending on the available memory, this value can be changed

...

additional arguments, as for writeRaster

Author

Babak Naimi

https://www.r-gis.net/

https://www.biogeoinformatics.org

Details

predict uses the fitted models in the sdmModel to generate the prediction given newdata. A raster (if newdata is Raster object) or data.frame (if newdata is data.frame) will be created.

The predictions can be generated for a specific set of models in the input sdmModels by determining either or a combination of the name of

For each prediction, a name is assigned which is kind of abbreviation or codding that tells which species, which method, which replication method, and which run is the prediction for. If the output is a Raster object, setZ function can be used to get a full name of each layer.

References

Naimi, B., Araujo, M.B. (2016) sdm: a reproducible and extensible R platform for species distribution modelling, Ecography, 39:368-375, DOI: 10.1111/ecog.01881

See Also

#

Examples

if (FALSE) {

file <- system.file("external/species.shp", package="sdm") # get the location of the species data

species <- shapefile(file) # read the shapefile

path <- system.file("external", package="sdm") # path to the folder contains the data

lst <- list.files(path=path,pattern='asc$',full.names = T) # list the name of the raster files 


# stack is a function in the raster package, to read/create a multi-layers raster dataset
preds <- stack(lst) # making a raster object

d <- sdmData(formula=Occurrence~., train=species, predictors=preds)

d

# fit the models (5 methods, and 10 replications using bootstrapping procedure):
m <- sdm(Occurrence~.,data=d,methods=c('rf','tree','fda','mars','svm'),
          replicatin='boot',n=10)
    
# predict for all the methods and replications:    
p1 <- predict(m, newdata=preds, filename='preds.img')
plot(p1)

# predict for all the methods but take the mean over all replications for each replication method:
p2 <- predict(m, newdata=preds, filename='preds.img',mean=T)
plot(p2)

}