Abstract
Machine learning (ML) has great potential to drive scientific discovery by harvesting data from images of herbarium specimens—preserved plant material curated in natural history collections—but ML techniques have only recently been applied to this rich resource. ML has particularly strong prospects for the study of plant phenological events such as growth and reproduction. As a major indicator of climate change, driver of ecological processes, and critical determinant of plant fitness, plant phenology is an important frontier for the application of ML techniques for science and society. In the present article, we describe a generalized, modular ML workflow for extracting phenological data from images of herbarium specimens, and we discuss the advantages, limitations, and potential future improvements of this workflow. Strategic research and investment in specimen-based ML methods, along with the aggregation of herbarium specimen data, may give rise to a better understanding of life on Earth.
Highlights
Machine learning (ML) has great potential to drive scientific discovery by harvesting data from images of herbarium specimens—preserved plant material curated in natural history collections—but ML techniques have only recently been applied to this rich resource
As a major indicator of climate change, driver of ecological processes, and critical determinant of plant fitness, plant phenology is an important frontier for the application of ML techniques for science and society
We describe a generalized, modular ML workflow for extracting phenological data from images of herbarium specimens, and we discuss the advantages, limitations, and potential future improvements of this workflow
Summary
Machine Learning Using Digitized Herbarium Specimens to Advance Phenological Research. Critical questions remain about the effects and interactions of climate, traits, geography, and phylogeny on the phenological sensitivities of plants and how these effects propagate throughout ecosystems (box 1) These factors could play key roles in understanding, predicting, and potentially ameliorating environmental changes that threaten biodiversity and humankind. Herbarium staff might record the presence or absence of reproductive structures while transcribing specimen data, or, more commonly, researchers classify phenological traits from physical specimens or specimen images for specific projects. Such methods are time and labor intensive, and the accuracy and precision of the resulting phenological annotations depend on the botanical expertise and consistency of the scorer, as well as on how the relevant anatomical structures can be identified on dried, pressed plants. Computational environment and personnel resources which allow a combination of several tasks, including data acquisition, storage, management, mining, visualization, and analysis
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
