Search for: All records

Abstract PremiseAmong the slowest steps in the digitization of natural history collections is converting imaged labels into digital text. We present here a working solution to overcome this long‐recognized efficiency bottleneck that leverages synergies between community science efforts and machine learning approaches. MethodsWe present two new semi‐automated services. The first detects and classifies typewritten, handwritten, or mixed labels from herbarium sheets. The second uses a workflow tuned for specimen labels to label text using optical character recognition (OCR). The label finder and classifier was built via humans‐in‐the‐loop processes that utilize the community science Notes from Nature platform to develop training and validation data sets to feed into a machine learning pipeline. ResultsOur results showcase a >93% success rate for finding and classifying main labels. The OCR pipeline optimizes pre‐processing, multiple OCR engines, and post‐processing steps, including an alignment approach borrowed from molecular systematics. This pipeline yields >4‐fold reductions in errors compared to off‐the‐shelf open‐source solutions. The OCR workflow also allows human validation using a custom Notes from Nature tool. DiscussionOur work showcases a usable set of tools for herbarium digitization including a custom‐built web application that is freely accessible. Further work to better integrate these services into existing toolkits can support broad community use. 

Abstract PremisePteridophytes—vascular land plants that disperse by spores—are a powerful system for studying plant evolution, particularly with respect to the impact of abiotic factors on evolutionary trajectories through deep time. However, our ability to use pteridophytes to investigate such questions—or to capitalize on the ecological and conservation‐related applications of the group—has been impaired by the relative isolation of the neo‐ and paleobotanical research communities and by the absence of large‐scale biodiversity data sources. MethodsHere we present the Pteridophyte Collections Consortium (PCC), an interdisciplinary community uniting neo‐ and paleobotanists, and the associated PteridoPortal, a publicly accessible online portal that serves over three million pteridophyte records, including herbarium specimens, paleontological museum specimens, and iNaturalist observations. We demonstrate the utility of the PteridoPortal through discussion of three example PteridoPortal‐enabled research projects. ResultsThe data within the PteridoPortal are global in scope and are queryable in a flexible manner. The PteridoPortal contains a taxonomic thesaurus (a digital version of a Linnaean classification) that includes both extant and extinct pteridophytes in a common phylogenetic framework. The PteridoPortal allows applications such as greatly accelerated classic floristics, entirely new “next‐generation” floristic approaches, and the study of environmentally mediated evolution of functional morphology across deep time. DiscussionThe PCC and PteridoPortal provide a comprehensive resource enabling novel research into plant evolution, ecology, and conservation across deep time, facilitating rapid floristic analyses and other biodiversity‐related investigations, and providing new opportunities for education and community engagement.