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.1 Note that in this paper "morphology" should be understood in its biological sense, that is, the visually identifiable properties of an object, rather than in its computer vision sense, that is, the numerical characteristics derived from the binary mask of the object (its "imprint" in the image).
Diatoms, a major component of the large-sized phytoplankton, are able to produce and release polyunsaturated aldehydes after cell disruption (potential PUAs or pPUA). These organisms are dominant in the large phytoplankton fraction (>10 µm) in the Strait of Gibraltar, the only connection between the Mediterranean Sea and the Atlantic Ocean. In this area, the hydrodynamics exerts a strong control on the composition and physiological state of the phytoplankton. This environment offers a great opportunity to analyze and compare the little known distribution of larger sized PUA producers in nature and, moreover, to study how environmental variables could affect the ranges and potential distribution of these compounds. Our results showed that, at both tidal regimes studied (Spring and Neap tides), diatoms in the Strait of Gibraltar are able to produce three aldehydes: Heptadienal, Octadienal and Decadienal, with a significant dominance of Decadienal production. The PUA released by mechanical cell disruption of large-sized collected cells (pPUA) ranged from 0.01 to 12.3 pmol from cells in 1 L, and from 0.1 to 9.8 fmol cell−1. Tidal regime affected the abundance, distribution and the level of physiological stress of diatoms in the Strait. During Spring tides, diatoms were more abundant, usually grouped nearer the coastal basin and showed less physiological stress than during Neap tides. Our results suggest a significant general increase in the pPUA productivity with increasing physiological stress for the cell also significantly associated to low nitrate availability.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.