Machine learning techniques to characterise functional traits of plankton image data

morten.iversen [ at ]


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.

Item Type
Primary Division
Primary Topic
Helmholtz Cross Cutting Activity (2021-2027)
Research Networks
Publication Status
Eprint ID
DOI 10.1002/lno.12101

Cite as
Orenstein, E. , Ayata, S. D. , Maps, F. , Becker, É. , Benedetti, F. , Biard, T. , de Garidel-Thoron, T. , Ellen, J. , Ferrario, F. , Giering, S. , Guy-Haim, T. , Hoebeke, L. , Iversen, M. , Kiorboe, T. , Lalonde, J. F. , Lana, A. , Laviale, M. , Lombard, F. , Lorimer, T. , Martini, S. , Meyer, A. , Möller, K. O. , Niehoff, B. , Ohman, M. , Pradalier, C. , Romagnan, J. B. , Schröder, S. M. , Sonnet, V. , Sosik, H. , Stemmann, L. , Stock, M. , Terbiyik-Kurt, T. , Valcárcel-Pérez, N. , Vilgrain, L. , Wacquet, G. , Waite, A. and Irisson, J. O. (2022): Machine learning techniques to characterise functional traits of plankton image data , Limnology and Oceanography . doi: 10.1002/lno.12101



Research Platforms

Edit Item Edit Item