View source: R/get_important_rasters.R
runENMeval | R Documentation |
This function takes as input the object output from preparte_rasters() and the background partitioning method you would like to use (see ENMeval documentation). You can visualize how the partitioning methods will look by viewing the PDF output from partition_raster_bg. See ?partition_raster_bg for more info.
runENMeval(
env.list,
bg,
partition.method,
parallel = FALSE,
np = 2,
RMvalues = seq(0.5, 4, 0.5),
feature.classes = c("L", "LQ", "H", "LQH", "LQHP", "LQHPT"),
categoricals = NULL,
algorithm = "maxent.jar"
)
env.list |
Object output from prepare_rasters() function |
bg |
Object with background points; generated from partition_raster_bg. If NULL, the background layer will be calculated for you. |
partition.method |
Method used for background point partitioning |
parallel |
If TRUE, ENMeval is run parallelized with np CPU cores |
np |
Number of parallel cores to use if parallel = TRUE |
RMvalues |
Vector of non-negative regularization multiplier values. Higher values impose a stronger penalty on model complexity |
feature.classes |
Character vector of feature classes to be used |
categoricals |
Vector indicating which (if any) of the input environmental layers are categorical. |
algorithm |
Character vector. Defaults to dismo's maxent.jar |
ENMeval object
eval.par <- runENMeval(env.list = envList,
bg = bg,
partition.method = "checkerboard1",
parallel = FALSE,
RMvalues = seq(0.5, 4, 0.5),
feature.classes = c("L",
"LQ",
"H",
"LQH",
"LQHP",
"LQHPT")
categoricals = NULL,
algorithm = "maxent.jar")
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.