The Herbarium 2021 Half-Earth Challenge Dataset and Machine Learning Competition.

Herbarium sheets present a unique view of the world's botanical history, evolution, and biodiversity. This makes them an all-important data source for botanical research. With the increased digitization of herbaria worldwide and advances in the domain of fine-grained visual classification which can facilitate automatic identification of herbarium specimen images, there are many opportunities for supporting and expanding research in this field. However, existing datasets are either too small, or not diverse enough, in terms of represented taxa, geographic distribution, and imaging protocols. Furthermore, aggregating datasets is difficult as taxa are recognized under a multitude of names and must be aligned to a common reference. We introduce the Herbarium 2021 Half-Earth dataset: the largest and most diverse dataset of herbarium specimen images, to date, for automatic taxon recognition. We also present the results of the Herbarium 2021 Half-Earth challenge, a competition that was part of the Eighth Workshop on Fine-Grained Visual Categorization (FGVC8) and hosted by Kaggle to encourage the development of models to automatically identify taxa from herbarium sheet images.

Identifying gaps in the photographic record of the vascular plant flora of the Americas.

Field photographs of plant species are crucial for research and conservation, but the lack of a centralized database makes them difficult to locate. We surveyed 25 online databases of field photographs and found that they harboured only about 53% of the approximately 125,000 vascular plant species of the Americas. These results reflect the urgent need for a centralized database that can both integrate and complete the photographic record of the world's flora.

An algorithm competition for automatic species identification from herbarium specimens.

PREMISE: Plant biodiversity is threatened, yet many species remain undescribed. It is estimated that >50% of undescribed species have already been collected and are awaiting discovery in herbaria. Robust automatic species identification algorithms using machine learning could accelerate species discovery. METHODS: To encourage the development of an automatic species identification algorithm, we submitted our Herbarium 2019 data set to the Fine-Grained Visual Categorization sub-competition (FGVC6) hosted on the Kaggle platform. We chose to focus on the flowering plant family Melastomataceae because we have a large collection of imaged herbarium specimens (46,469 specimens representing 683 species) and taxonomic expertise in the family. As is common for herbarium collections, some species in this data set are represented by few specimens and others by many. RESULTS: In less than three months, the FGVC6 Herbarium 2019 Challenge drew 22 teams who entered 254 models for Melastomataceae species identification. The four best algorithms identified species with >88% accuracy. DISCUSSION: The FGVC competitions provide a unique opportunity for computer vision and machine learning experts to address difficult species-recognition problems. The Herbarium 2019 Challenge brought together a novel combination of collections resources, taxonomic expertise, and collaboration between botanists and computer scientists.

Increasing the efficiency of digitization workflows for herbarium specimens.

The New York Botanical Garden Herbarium has been databasing and imaging its estimated 7.3 million plant specimens for the past 17 years. Due to the size of the collection, we have been selectively digitizing fundable subsets of specimens, making successive passes through the herbarium with each new grant. With this strategy, the average rate for databasing complete records has been 10 specimens per hour. With 1.3 million specimens databased, this effort has taken about 130,000 hours of staff time. At this rate, to complete the herbarium and digitize the remaining 6 million specimens, another 600,000 hours would be needed. Given the current biodiversity and economic crises, there is neither the time nor money to complete the collection at this rate.Through a combination of grants over the last few years, The New York Botanical Garden has been testing new protocols and tactics for increasing the rate of digitization through combinations of data collaboration, field book digitization, partial data entry and imaging, and optical character recognition (OCR) of specimen images. With the launch of the National Science Foundation's new Advancing Digitization of Biological Collections program, we hope to move forward with larger, more efficient digitization projects, capturing data from larger portions of the herbarium at a fraction of the cost and time.