Linking satellites to genes with machine learning to estimate phytoplankton community structure from space

Ocean science, vol. 20, pp. 217–239

Abstract

Ocean color remote sensing has been used for more than 2 decades to estimate primary productivity. Approaches have also been developed to disentangle phytoplankton community structure based on spectral data from space, in particular when combined with in situ measurements of photosynthetic pigments. Here, we propose a new ocean color algorithm to derive the relative cell abundance of seven phytoplankton groups, as well as their contribution to total chlorophyll a (Chl a ) at the global scale. Our algorithm is based on machine learning and has been trained using remotely sensed parameters (reflectance, backscattering, and attenuation coefficients at different wavelengths, plus temperature and Chl a ) combined with an omics-based biomarker developed using Tara Oceans data representing a single-copy gene encoding a component of the photosynthetic machinery that is present across all phytoplankton, including both prokaryotes and eukaryotes. It differs from previous methods which rely on diagnostic pigments to derive phytoplankton groups. Our methodology provides robust estimates of the phytoplankton community structure in terms of relative cell abundance and contribution to total Chl a concentration. The newly generated datasets yield complementary information about different aspects of phytoplankton that are valuable for assessing the contributions of different phytoplankton groups to primary productivity and inferring community assembly processes. This makes remote sensing observations excellent tools to collect essential biodiversity variables (EBVs) and provide a foundation for developing marine biodiversity forecasts.

Authors 6

1. Roy El Hourany

   Université du littoral côte d'opale · Laboratoire d’Océanologie et de Géosciences

   Affiliation as printed

   LOG - Laboratoire d’Océanologie et de Géosciences (LOG) - UMR 8187 (28 avenue Foch - BP 80 - 62930 Wimereux - France)

   ULCO - Université du Littoral Côte d'Opale (1, place de l'Yser - BP 71022 59375 Dunkerque Cedex - France)

2. Juan José Pierella Karlusich

   École Normale Supérieure - PSL · Harvard University · Institut de Biologie de l'École Normale Supérieure

   Affiliation as printed

   GOSEE - Global Oceans Systems Ecology & Evolution - Tara Oceans (3 rue Michel-Ange, 75016 Paris - France)

   Harvard University (Massachusetts Hall, Cambridge, MA 02138 - United States)

   IBENS - Institut de biologie de l'ENS Paris (46, Rue d’Ulm 75005 Paris - France)

3. Lucie Zinger Aachen Naturalis Biodiversity Center Naturalis Biodiversity Center [Leiden] (Darwinweg 2

   Centre National de la Recherche Scientifique · Université Paris Sciences et Lettres · École Normale Supérieure - PSL · Inserm · Institut de Biologie de l'École Normale Supérieure · Naturalis Biodiversity Center

   Affiliation as printed

   Institut de Biologie de l'Ecole Normale Supérieure (IBENS), Ecole Normale Supérieure, CNRS, INSERM, Université PSL, 75005 Paris, France

   Naturalis Biodiversity Center, 2300 RA Leiden, the Netherlands

   Research Federation for the study of Global Ocean Systems Ecology and Evolution, FR2022/Tara GOSEE, 75016 Paris, France

   GOSEE - Global Oceans Systems Ecology & Evolution - Tara Oceans (3 rue Michel-Ange, 75016 Paris - France)

   IBENS - Institut de biologie de l'ENS Paris (46, Rue d’Ulm 75005 Paris - France)

   Naturalis Biodiversity Center [Leiden] (Darwinweg 2, 2333 CR Leiden - Netherlands)

4. Hubert Loisel

   Centre National de la Recherche Scientifique · Institut de Recherche pour le Développement · Université de Lille · Université du littoral côte d'opale · Laboratoire d’Océanologie et de Géosciences

   Affiliation as printed

   Univ. Littoral Côte d’Opale, Univ. Lille, CNRS, IRD, UMR 8187, LOG, Laboratoire d’Océanologie et de Géosciences, 62930 Wimereux, France

   LOG - Laboratoire d’Océanologie et de Géosciences (LOG) - UMR 8187 (28 avenue Foch - BP 80 - 62930 Wimereux - France)

   ULCO - Université du Littoral Côte d'Opale (1, place de l'Yser - BP 71022 59375 Dunkerque Cedex - France)

5. Marina Lévy corresponding

   Centre National de la Recherche Scientifique · Sorbonne Université · Institut de Recherche pour le Développement · Institut Pierre-Simon Laplace · Laboratoire d'Océanographie et du Climat : Expérimentations et Approches Numériques

   Affiliation as printed

   Sorbonne Université, LOCEAN-IPSL, Laboratoire d'Océanographie et du Climat; Expérimentations et Approches Numériques, CNRS, IRD, MNHN, 75005 Paris, France

   LOCEAN - Laboratoire d'Océanographie et du Climat : Expérimentations et Approches Numériques (case 100 - 4 place Jussieu - 75252 PARIS CEDEX 05 ; Institut de Recherche pour le Développement - Centre de recherche d'Ile-de-France - 32 avenue Henri Varagnat - 93143 Bondy Cedex - France)

   LOCEAN-PROTEO - Processus et interactions de fine échelle océanique (France)

6. Chris Bowler corresponding

   Centre National de la Recherche Scientifique · Université Paris Sciences et Lettres · École Normale Supérieure - PSL · Inserm · Institut de Biologie de l'École Normale Supérieure

   Affiliation as printed

   Institut de Biologie de l'Ecole Normale Supérieure (IBENS), Ecole Normale Supérieure, CNRS, INSERM, Université PSL, 75005 Paris, France

   Research Federation for the study of Global Ocean Systems Ecology and Evolution, FR2022/Tara GOSEE, 75016 Paris, France

   GOSEE - Global Oceans Systems Ecology & Evolution - Tara Oceans (3 rue Michel-Ange, 75016 Paris - France)

   IBENS - Institut de biologie de l'ENS Paris (46, Rue d’Ulm 75005 Paris - France)