BROADCASTS.com

'Plankton" consists of phytoplankton (~plants) and zooplankton (-animals). It represents the basis of the ocean food chain and it includes many species; it's a very complex 'multi-species soup' representing a true science frontier hardly tackled, understood or managed yet. 

Copepods are part of that taxonomic set up and they contribute usually to the majority - up to 70% -  of zooplankton abundance in oceans. Using field data of the Italian National Antarctic Program from the 1980s and 1990s here we model-predict in an interdisciplinary international team effort for 26 copepod species at three ocean depth classes (0-10m, 11-70m, 71-750m) the relative index of occurrence (RIO) for the wider study area of the Ross Sea Region Marine Protected Area (a world-record MPA and ocean wilderness area of global size and relevance). This research uses Machine Learning/AI ensembles and Open Source Geographic Information System (GIS) methods to generalize from the Open Access dataset available from the Global Biodiversity Information Facility (GBIF.org) using the 'Macroscope predictors' (see Huettmann et al. 2015 for details, source and use). Further details are provided in Grillo et al. (2022; compare also with Pinkerton et al. 2010).

This work matters as a global workflow template and it allows to obtain 3D models in GIS for plankton abundance, e.g. as needed for foraging estimates of marine mammals, penguins and fisheries. It can also be used for life-history research, carbon sequestration work in climate models as well as for baselines in carrying capacity formulas for fisheries and generic predator-prey studies.

The relevance of sound harvest models for krill and fish, e.g. in the so-called 'experimental' fisheries work with CCAMLR and the MPA in the Ross Sea has been outlined by Ainley et al. (2012) and others. Here we offer a solution towards sustainability in times of a generic ocean crisis.

References (selection; in order of citation)

Grillo M, F. Huettmann, L. Guglielmo and S. Schiaparelli (2022) Three-Dimensional Quantification of Copepods Predictive Distributions in the Ross Sea: First Data Based on a Machine Learning Model Approach and Open Access (FAIR) Data. Diversity 14:355. https://doi.org/10.3390/d14050355

Huettmann, F., M.S. Schmid, and G.R.W. Humphries (2015)  A First Overview of Open Access Digital Data for the Ross Sea: Complexities, Ethics, and Management Opportunities. Hydrobiologia 2015, 761, 97–119.

Pinkerton, M. H., A.N. Smith, B. Raymond, G.W. Hosie, B. Sharp, J.R. Leathwick and J.M. Bradford-Grieve (2010). Spatial and seasonal distribution of adult Oithona similis in the Southern Ocean: predictions using boosted regression trees. Deep Sea Research Part I: Oceanographic Research Papers 57: 469-485.

Ainley, D.G., C.M. Brooks, J.T. Eastman and M. Massaro (2012) Unnatural Selection of Antarctic Toothfish in the Ross Sea, Antarctica. In Protection of the Three Poles; Springer: Berlin/Heidelberg, Germany, pp. 53–75.0

(Photo credit: Andrei Savitsky - Own work, CC BY-SA 4.0, https://commons.wikimedia.org/w/index.php?curid=78800127)