STEM-LM: Spatio-Temporal Ecological Modeling via Masked Language Model for Multi-Species Distribution
Jacky Kaiyuan Li, Wonseop Lim, Robin Rheem, Fiona Margaret Callahan, Levi Yoder Raskin, Maya Lemmon-Kishi, Rasmus Nielsen
STEM-LM uses masked language modeling to predict multi-species distributions by treating species presence as tokens in a spatio-temporal 'sentence', achieving high discrimination on ecological datasets.
bioRxiv · Oct 6, 2026 · PreprintEcology