A list of datasets suitable for large-scale Species Distribution Model (SDM) benchmarking
Data with species occurrences of plants for France and U.S. along with covariates and satellite imagery.
Paper: https://arxiv.org/abs/2004.04192
Data: https://lila.science/datasets/geolifeclef-2020/
Data on hexagonal grids for 3,030 variables (climate, human related, soil, etc.) and occurrences for 900 extant and extinct large mammals.
Paper: https://www.nature.com/articles/s41597-023-01966-x
Data: https://etsin.fairdata.fi/dataset/552c6ac2-4677-4a7b-952f-1632b2b9c335
Data from: A comprehensive evaluation of predictive performance of 33 species distribution models at species and community levels
Contains 5 datasets of species occurrences and environmental variables for different organismal groups and different areas. Dataset size ranges from 50 to 242 species. Was used to test joint species distribution model frameworks (JSDMs).
Paper: https://esajournals.onlinelibrary.wiley.com/doi/full/10.1002/ecm.1370
Data: https://zenodo.org/record/2637812#.ZGexrs7MKM9
Paper:
Data: