Skip to main content
Dryad logo

Predictor complexity and feature selection affect Maxent model transferability: evidence from global freshwater invasive species

Citation

Low, Bi Wei; Zeng, Yiwen; Tan, Heok Hui; Yeo, Darren C. J. (2021), Predictor complexity and feature selection affect Maxent model transferability: evidence from global freshwater invasive species, Dryad, Dataset, https://doi.org/10.5061/dryad.ttdz08kww

Abstract

This dataset contains the following:

  1. Occurrence datasets of five global freshwater invasive species (African sharptooth catfish Clarias gariepinus, Mozambique tilapia Oreochromis mossambicus, American bullfrog Lithobates catesbeianus, red swamp crayfish Procambarus clarkii, and Australian redclaw crayfish Cherax quadricarinatus)
  2. Background points for presence-only ecological niche modelling (e.g., Maxent)
  3. Example R script (with annotations inline) to conduct model tuning and transferability assessments using Maxent

Methods

Occurence datasets for five species were aggregated from published literature, online databases, and natural history museum collections (see Appendix S1 in Supporting Information of journal article for data sources). Occurrences were further thinned using the 'thin' function (R package 'spThin') with a thinning distance of 50 km.

Usage Notes

Global climatic layers for Maxent model calibration can be obtained from WorldClim (https://www.worldclim.org/) and the Intergovernmental Panel on Climate Change (IPCC) Data Distribution Centre (http://www.ipcc-data.org).

Funding

Singapore Ministry of Education , Award: R-154-000-633-112

Ah Meng Memorial Conservation Fund , Award: R-154-000-617-720

Lee Kong Chian Natural History Museum

National Research Foundation Singapore, Award: NRF-CSC-ICFC2017-05

Singapore Ministry of Education, Award: R-154-000-633-112

Ah Meng Memorial Conservation Fund, Award: R-154-000-617-720

Lee Kong Chian Natural History Museum