acePetal to the metal: The slow road to automating large-scale phenology labeling for herbarium specimens
Premise Herbarium specimens represent critical historical records of plant phenology, yet automating annotation of reproductive structures remains challenging given the diversity of floral morphologies, specimen age and quality, and image quality. Methods Here, we present a machine learning pipeline that uses an ensemble modeling approach to detect flowers on herbarium specimens and deliver these data to the phenology research community. After testing multiple strategies for generating training data, we found th…
An ensemble machine learning pipeline detected flowers on herbarium specimens with relatively strong accuracy and labeled 11.1 million of 22 million records, expanding taxonomic and temporal coverage when integrated into Phenobase.
The same ensemble pipeline showed moderately high false negative rates for floral structures and only 2.9 million of the 11.1 million flower-labeled records had complete metadata necessary for downstream phenology research.
Performance was constrained by diversity of floral morphologies, specimen age and quality, and image quality, with moderately high false negative rates and dependence on expert-curated training data and complete label digitization.
Evidence
- Peer-reviewedApplications in Plant Sciences2026-10-01
How should this claim be treated?
Truvace Impact Record TRV-2026-1263, v1: “Petal to the metal: The slow road to automating large-scale phenology labeling for herbarium specimens.” Truvace, 2026-10-03. /record/TRV-2026-1263 (accessed at citation time). sha256 cb5eead4169d63a3…
Calibration history
Every change to this record since certification, in the open. None yet — the reading has held since it entered the record.
Certified into the record
How to verify without trusting this page
Fetch the canonical text of any version from /api/record/TRV-2026-1263 and hash it yourself — for example shasum -a 256 on the saved canonical field. The result must equal content_hash, and each version’s text ends with prev:followed by the prior version’s hash (version 1 chains to 64 zeros). If a single character of any version had been altered since certification, the chain would not reproduce.