Machine learning techniques to characterize functional traits of plankton from image data.

Plankton imaging systems supported by automated classification and analysis have improved ecologists' ability to observe aquatic ecosystems. Today, we are on the cusp of reliably tracking plankton populations with a suite of lab-based and in situ tools, collecting imaging data at unprecedentedly fine spatial and temporal scales. But these data have potential well beyond examining the abundances of different taxa; the individual images themselves contain a wealth of information on functional traits. Here, we outline traits that could be measured from image data, suggest machine learning and computer vision approaches to extract functional trait information from the images, and discuss promising avenues for novel studies. The approaches we discuss are data agnostic and are broadly applicable to imagery of other aquatic or terrestrial organisms.

Making marine image data FAIR.

Underwater images are used to explore and monitor ocean habitats, generating huge datasets with unusual data characteristics that preclude traditional data management strategies. Due to the lack of universally adopted data standards, image data collected from the marine environment are increasing in heterogeneity, preventing objective comparison. The extraction of actionable information thus remains challenging, particularly for researchers not directly involved with the image data collection. Standardized formats and procedures are needed to enable sustainable image analysis and processing tools, as are solutions for image publication in long-term repositories to ascertain reuse of data. The FAIR principles (Findable, Accessible, Interoperable, Reusable) provide a framework for such data management goals. We propose the use of image FAIR Digital Objects (iFDOs) and present an infrastructure environment to create and exploit such FAIR digital objects. We show how these iFDOs can be created, validated, managed and stored, and which data associated with imagery should be curated. The goal is to reduce image management overheads while simultaneously creating visibility for image acquisition and publication efforts.

Predation risk triggers copepod small-scale behavior in the Baltic Sea.

Predators not only have direct impact on biomass but also indirect, non-consumptive effects on the behavior their prey organisms. A characteristic response of zooplankton in aquatic ecosystems is predator avoidance by diel vertical migration (DVM), a behavior which is well studied on the population level. A wide range of behavioral diversity and plasticity has been observed both between- as well as within-species and, hence, investigating predator-prey interactions at the individual level seems therefore essential for a better understanding of zooplankton dynamics. Here we applied an underwater imaging instrument, the video plankton recorder (VPR), which allows the non-invasive investigation of individual, diel adaptive behavior of zooplankton in response to predators in the natural oceanic environment, providing a finely resolved and continuous documentation of the organisms' vertical distribution. Combing observations of copepod individuals observed with the VPR and hydroacoustic estimates of predatory fish biomass, we here show (i) a small-scale DVM of ovigerous Pseudocalanus acuspes females in response to its main predators, (ii) in-situ observations of a direct short-term reaction of the prey to the arrival of the predator and (iii) in-situ evidence of pronounced individual variation in this adaptive behavior with potentially strong effects on individual performance and ecosystem functioning.