Harnessing Large-Scale Herbarium Image Datasets Through Representation Learning.

The mobilization of large-scale datasets of specimen images and metadata through herbarium digitization provide a rich environment for the application and development of machine learning techniques. However, limited access to computational resources and uneven progress in digitization, especially for small herbaria, still present barriers to the wide adoption of these new technologies. Using deep learning to extract representations of herbarium specimens useful for a wide variety of applications, so-called "representation learning," could help remove these barriers. Despite its recent popularity for camera trap and natural world images, representation learning is not yet as popular for herbarium specimen images. We investigated the potential of representation learning with specimen images by building three neural networks using a publicly available dataset of over 2 million specimen images spanning multiple continents and institutions. We compared the extracted representations and tested their performance in application tasks relevant to research carried out with herbarium specimens. We found a triplet network, a type of neural network that learns distances between images, produced representations that transferred the best across all applications investigated. Our results demonstrate that it is possible to learn representations of specimen images useful in different applications, and we identify some further steps that we believe are necessary for representation learning to harness the rich information held in the worlds' herbaria.

People are essential to linking biodiversity data.

People are one of the best known and most stable entities in the biodiversity knowledge graph. The wealth of public information associated with people and the ability to identify them uniquely open up the possibility to make more use of these data in biodiversity science. Person data are almost always associated with entities such as specimens, molecular sequences, taxonomic names, observations, images, traits and publications. For example, the digitization and the aggregation of specimen data from museums and herbaria allow us to view a scientist's specimen collecting in conjunction with the whole corpus of their works. However, the metadata of these entities are also useful in validating data, integrating data across collections and institutional databases and can be the basis of future research into biodiversity and science. In addition, the ability to reliably credit collectors for their work has the potential to change the incentive structure to promote improved curation and maintenance of natural history collections.

Impact of e-publication changes in the International Code of Nomenclature for algae, fungi and plants (Melbourne Code, 2012) - did we need to "run for our lives"?

BACKGROUND: At the Nomenclature Section of the XVIII International Botanical Congress in Melbourne, Australia (IBC), the botanical community voted to allow electronic publication of nomenclatural acts for algae, fungi and plants, and to abolish the rule requiring Latin descriptions or diagnoses for new taxa. Since the 1st January 2012, botanists have been able to publish new names in electronic journals and may use Latin or English as the language of description or diagnosis. RESULTS: Using data on vascular plants from the International Plant Names Index (IPNI) spanning the time period in which these changes occurred, we analysed trajectories in publication trends and assessed the impact of these new rules for descriptions of new species and nomenclatural acts. The data show that the ability to publish electronically has not "opened the floodgates" to an avalanche of sloppy nomenclature, but concomitantly neither has there been a massive expansion in the number of names published, nor of new authors and titles participating in publication of botanical nomenclature. CONCLUSIONS: The e-publication changes introduced in the Melbourne Code have gained acceptance, and botanists are using these new techniques to describe and publish their work. They have not, however, accelerated the rate of plant species description or participation in biodiversity discovery as was hoped.

Actionable, long-term stable and semantic web compatible identifiers for access to biological collection objects.

With biodiversity research activities being increasingly shifted to the web, the need for a system of persistent and stable identifiers for physical collection objects becomes increasingly pressing. The Consortium of European Taxonomic Facilities agreed on a common system of HTTP-URI-based stable identifiers which is now rolled out to its member organizations. The system follows Linked Open Data principles and implements redirection mechanisms to human-readable and machine-readable representations of specimens facilitating seamless integration into the growing semantic web. The implementation of stable identifiers across collection organizations is supported with open source provider software scripts, best practices documentations and recommendations for RDF metadata elements facilitating harmonized access to collection information in web portals. Database URL: : http://cetaf.org/cetaf-stable-identifiers.