Russell Dinnage

The paper presents a machine learning pipeline for automating flower detection on herbarium specimens, resulting in 11.1 million labeled records but highlighting the need for full metadata digitization.

PhenoVision-Leaf uses a Vision Transformer model trained on crowdsourced data to generate global-scale leaf phenology observations from iNaturalist records.

PhenoVision automates plant phenology data extraction from field images, achieving high accuracy in detecting flowers and fruits, and expands global phenology data coverage.

NicheFlow is a foundation model for species distribution modeling that improves predictions for rare species using generative AI, showing strong performance in zero-shot tasks and capturing ecological patterns.