AUTHOR=Drago Laetitia , Panaïotis Thelma , Irisson Jean-Olivier , Babin Marcel , Biard Tristan , Carlotti François , Coppola Laurent , Guidi Lionel , Hauss Helena , Karp-Boss Lee , Lombard Fabien , McDonnell Andrew M. P. , Picheral Marc , Rogge Andreas , Waite Anya M. , Stemmann Lars , Kiko Rainer 

TITLE=Global Distribution of Zooplankton Biomass Estimated by In Situ Imaging and Machine Learning

JOURNAL=Frontiers in Marine Science

VOLUME=Volume 9 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/marine-science/articles/10.3389/fmars.2022.894372

DOI=10.3389/fmars.2022.894372

ISSN=2296-7745

ABSTRACT=Zooplankton plays a major role in ocean food webs and biogeochemical cycles and provides major ecosystem services as a main driver of the biological carbon pump and a pivotal actor in sustaining fish communities. Zooplankton is also sensitive to its environment and reacts to its changes. To better understand the importance of zooplankton and to inform prognostic models that try to represent them, spatially-resolved biomass estimates of key plankton taxa are desirable. In this study, we for the first time predict the global biomass distribution of 19 zooplankton taxa (1-50 mm Equivalent Spherical Diameter) using observations by the Underwater Vision Profiler 5, a quantitative in situ imaging instrument. After computer-assisted classification of 466,872 organisms from more than 3,478 profiles (0-500 m) obtained between 2008 and 2019 throughout the globe, we estimated their individual biovolume and converted it to biomass using taxa-specific factors. We then associated these biomass estimates with climatologies of environmental variables (temperature, salinity, oxygen, etc.), to build habitat models using boosted regression trees. The results reveal maximal zooplankton biomass values around 60°N and 55°S as well as minimal values around the oceanic gyres. An increased zooplankton biomass is predicted centered on the equator. Global integrated biomass (0-500 m) was estimated at 0.312 PgC. It was largely dominated by Copepoda (44%, mostly in polar regions), followed by Rhizaria (19%, mostly in inter tropical areas). The used machine learning approach is sensitive to the amount of training data and generates reliable predictions for abundant groups such as Copepoda (R2 ~ 50-61%) but not for rare ones (Ctenophora, Cnidaria, R2 < 5%). Still, this study offers a first protocol to estimate global, spatially resolved zooplankton biomass and community composition from in situ imaging observations of individual organisms. The underlying dataset was obtained within ten years, whereas similar approaches rely on data obtained using plankton nets gathered since about 1960. Increased use of digital imaging approaches should enable us to obtain zooplankton biomass distribution estimates at basin to global scales in shorter time frames in the future.