blockCV R package - Spatial and Environmental Blocking for K-Fold and LOO Cross-Validation
The package allows creating spatially or environmentally separated folds for cross-validation to provide a robust error estimation in spatially structured environments. Moreover, it permits to investigate and visualise the effective range of spatial autocorrelation in continuous raster covariates and point samples to find an initial realistic distance band to separate training and testing datasets spatially described in Valavi, R. et al. (2019),
https://doi.org/10.1111/2041-210X.13107.
Default
Identification
- Date ( Publication )
- 2023-06-04
- Status
- Completed
- Version
- 3.1.3
- Keywords
- k-fold validation
- Keywords
- cross validation
- Keywords
- spatial datasets
- Keywords
- R
- Access constraints
- License
- Use limitation
- https://cran.r-project.org/web/licenses/GPL-3
- OnLine resource
- CRAN link ( WWW:LINK-1.0-http--link )
- Required Services
- R (≥ 3.5.0)
- Topic Category
- Species distribution
- Service Category
- model preparation
- Service Category
- model evaluation
- Service Language
- eng
- Service TRL
- TRL 9 – Actual system proven in operational environment
- Service User Manual
- https://cran.r-project.org/web/packages/blockCV/blockCV.pdf