K. D. Erickson

Modeling the rarest of the rare: A comparison between joint species distribution models, ensembles of small models, and single-species models at extremely low sample sizes

This study compares modeling approaches for rare species at low sample sizes, finding that ensembles of small models perform better in discrimination tasks, while joint species models better estimate niche responses.

Including imprecisely georeferenced specimens improves accuracy of species distribution models and estimates of niche breadth

The paper improves species distribution models by including imprecisely georeferenced specimens, showing better accuracy and niche breadth estimates compared to using only precise records.

Occupancy-collection models: Towards bias-corrected modeling of species' distributions using unstructured occurrence data from museums and herbaria

This study adapts occupancy-detection models to correct biases in opportunistic species occurrence data from museums and citizen science, using Anacardiaceae in Florida as a case study.