Daijiang Li

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.

This study uses iNaturalist and herbarium data to show urban areas in the tropics have longer plant reproductive durations and weaker seasonality compared to rural areas.

NECTAR reconstructs pollinator-plant interaction networks from biodiversity data to guide habitat restoration, improving pollinator support by 2.4 times compared to random selection.

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.

The paper examines whether functional traits can explain phylogenetic signal in plant community composition using empirical data from Wisconsin forests.