Data and code from: Assessing the transferability of species distribution models: A cross-continental evaluation
- Source
- DataCite
- Published
- 2026
- License
- Creative Commons Zero v1.0 Universal
- Themes
- Invasive Species, Plants & Vegetation, Geospatial & GIS Data
About this dataset
To identify an appropriate method for assessing the transferability of species distribution models, the distribution of three invasive plant species was predicted using Maxent across different continents with datasets sourced from various continental combinations. The study confirmed that the conventional approach, namely using random holdout test datasets and the AUC (the area under the receiver operating characteristic curve), failed to reliably assess model transferability. Instead, using spatially independent test datasets and RWIP (correlation coefficient with the predictions from the model calibrated in the predicted region) provided a more robust evaluation approach. This dataset is the underlying data and codes of the study. It consists of four parts: distribution data, environmental data, Maxent predictions: Maxent output and Maxent values at point locations, and R codes...
How the data was collected
The source metadata does not specify a detailed collection methodology. Provenance: this record was harvested from DataCite and published by Dryad. Consult the original source for methodological details, temporal coverage, and access constraints.