Pauthenet Etienne auteur aut IRD Martinez Elodie auteur aut IRD Gorgues Thomas auteur aut IRD Roussillon Joana auteur aut IRD Drumetz L. auteur aut IRD Fablet R. auteur aut IRD Roux M. auteur aut IRD text journalArticle eng text/pdf reformatted digital access Phytoplankton sustains marine ecosystems and influences the global carbon cycle. This study analyzes trends in surface chlorophyll-a concentration (Schl), a proxy for phytoplankton biomass, using six of the most widely used merged satellite products. Significant regional variations are observed, with contrasting trends observed among different products. To assess if these trends can be related to changes in the environment or to bias in radiometric products, a convolutional neural network is used to examine the relationship between physical ocean variables versus Schl. The results suggest that the merging algorithm of Globcolour-GSM is not reliable for trend detection and that observed changes in Schl after 2012/2016 are not supported by changes of the physical ocean. These results emphasize the need for careful interpretation of satellite-derived Schl trends and highlight the potential of machine learning in understanding the complex interactions in marine ecosystems. specialized PACIFIQUE ATLANTIQUE OCEAN INDIEN 032MILPHY 034BIOVEG02 51 14 e2024GL108916 [10 ] 2024 0094-8276 https://www.documentation.ird.fr/hor/fdi:010087872 10.1029/2024gl108916 0094-8276 [F B010087872] https://www.documentation.ird.fr/hor/fdi:010087872 https://horizon.documentation.ird.fr/exl-doc/pleins_textes/2024-09/010087872.pdf IRD - Base Horizon / Pleins textes 2024-08-21 2025-11-06 fdi:010087872 fre