Ensemble automated approaches for producing high-quality herbarium digital records

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.