search

rvalavi / blockCV

The blockCV package creates spatially or environmentally separated training and testing folds for cross-validation to provide a robust error estimation in spatially structured environments. See
https://doi.org/10.1111/2041-210X.13107
GNU General Public License v3.0
109 stars 24 forks source link

Biomod2 pseudoabsences and blockCV #49

Closed amythor closed 4 months ago

amythor commented 4 months ago

Hey blockCV community,

I am not normally one to post on here but I am just wondering if it is possible to use the blockCV package to cross-validate SDMs created with biomod2 if you have used the biomod2 internal function to create pseudo absences?

I seem to be running into a problem trying to do this as it is not accounting for the 5 pseudoabsence generation repetitions I have created.

Any help is much appreciated!

rvalavi commented 4 months ago

Hi @amythor,

Unfortunately, at the moment, this is not possible unless the biomod developers incorporate blockCV internally (which, to my knowledge, they have not). If you want to use the internal pseudo-absence selection, you will need to utilize one of the spatial cross-validation methods provided by biomod itself.

I hope this helps.

amythor commented 4 months ago

Sounds good, thank you for your response!