Robert Guralnick

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.

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

The paper assesses protected habitat availability for the declining Loammi skipper butterfly in Florida, finding over half of its habitat is in protected areas.

The paper assesses how plant functional traits interact with regional threats to predict extinction risk, finding smaller herbaceous species are more vulnerable and some threats reduce extinction risk.

The paper examines how large-scale atmospheric circulation cells influence the migratory timing of eastern monarch butterflies, finding wind dynamics and atmospheric cells are key factors in spring arrival timing.

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

The paper examines diazotroph diversity in nodulating plants across the southeastern USA, finding host phylogeny strongly shapes symbiont composition and diversity.

This study finds that U.S. butterflies listed under the Endangered Species Act (ESA) receive more research attention, with increased publications after listing compared to non-listed species.

The paper examines how the loss of a color morph in woodland salamanders affects asymmetric character release and evolutionary rates between morphs.

This study shows that tectonic uplift and oceanic separation shape the distribution and speciation of Kapokapowai dragonflies in New Zealand.

This study identifies genes and adaptations in the blue dasher dragonfly that enable survival in urban environments and predicts its spread with urbanization.

This study reconstructs the phylogeny of Neotropical limenitidine butterflies to explore the evolution of mimicry patterns and their relationship with speciation.

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 evaluates the evolutionary balance between bat predation pressure and environmental constraints on moth tail length using phylogenetic and ecological data.

The paper examines avian elevational migration in the Western Ghats, finding that broader environmental tolerances, not climatic constraints, drive migration patterns across seasons.

The paper develops an ensemble method combining rule-based and large language model approaches to improve the accuracy of converting OCR text from herbarium labels into standardized digital data records.

The paper develops a computer vision model to automatically categorize color patterns in community science images, finding striped morphs of salamanders have wider niche breadth.