EUVIMEDObjevte EUVIMED
Open access · CC BY 4.0

Ensemble automated approaches for producing high‐quality herbarium digital records

Robert P Guralnick iD, Raphael LaFrance, Julie M Allen, Michael W Denslow

Applications in Plant Sciences · 2025-01 · 13 (1)

DOI: 10.1002/aps3.11623 ↗

At a glance

Journal article in Applications in Plant Sciences, published online on 2024-11-05. Written by Robert P Guralnick and 3 co-authors. Institution: Florida Museum of Natural History University of Florida Gainesville Florida USA. Cited 10 times so far (Crossref); 14 references. The full text is freely available (open access, CC BY 4.0).

AbstraktSubjectsBibliografické údajeCiteRelated studies

Abstract (original language)

Premise One of the slowest steps in digitizing natural history collections is converting labels associated with specimens into a digital data record usable for collections management and research. Here, we address how herbarium specimen labels can be converted into digital data records via extraction into standardized Darwin Core fields.

Methods

We first showcase the development of a rule‐based approach and compare outcomes with a large language model–based approach, in particular ChatGPT4. We next quantified omission and commission error rates across target fields for a set of labels transcribed using optical character recognition (OCR) for both approaches. For example, we find that ChatGPT4 often creates field names that are not Darwin Core compliant while rule‐based approaches often have high commission error rates.

Results

Our results suggest that these approaches each have different strengths and limitations. We therefore developed an ensemble approach that leverages the strengths of each individual method and documented that ensembling strongly reduced overall information extraction errors.

Discussion

This work shows that an ensemble approach has particular value for creating high‐quality digital data records, even for complicated label content. While human validation is still needed to ensure the best possible quality, automated approaches can speed digitization of herbarium specimen labels and are likely to be broadly usable for all natural history collection types.

Subjects

Author keywords

ChatGPTdigitizationensemble methodsinformation extractionlarge language modelsmachine learningnatural history collectionsnatural language processing

Authors and institutions

  • Florida Museum of Natural History University of Florida Gainesville Florida USA.
  • Department of Biological Sciences VirginiaTech Blacksburg Virginia USA.

ORCID profiles: Robert P Guralnick

Cite

APA

Guralnick, R. P., LaFrance, R., Allen, J. M., & Denslow, M. W. (2025). Ensemble automated approaches for producing high‐quality herbarium digital records. Applications in Plant Sciences, 13(1). https://doi.org/10.1002/aps3.11623

Vancouver

Guralnick RP, LaFrance R, Allen JM, Denslow MW. Ensemble automated approaches for producing high‐quality herbarium digital records. Applications in Plant Sciences. 2025;13(1). doi:10.1002/aps3.11623

BibTeX
@article{Guralnick2025,
  author = {Guralnick, Robert P and LaFrance, Raphael and Allen, Julie M and Denslow, Michael W},
  title = {Ensemble automated approaches for producing high‐quality herbarium digital records},
  journal = {Applications in Plant Sciences},
  year = {2025},
  volume = {13},
  number = {1},
  doi = {10.1002/aps3.11623}
}
Start for free →