AqQua seeks to create the first foundational pelagic imaging model by consolidating billions of images from diverse aquatic environments around the globe. These images capture a vast range of plankton species and organic particles and hold key insights into biodiversity and ecosystem health. By developing an AI model capable of classifying species, extracting biological traits, and estimating organic carbon content, AqQua will provide critical data necessary for understanding the biological carbon pump — a natural process that sequesters vast amounts of carbon from the atmosphere, significantly affecting global climate.
Distributed pelagic imaging techniques enable the sustained observation of aquatic life and its debris, comprehensively covering the earth’s water bodies down to the bottom of the deep sea. Each day, millions of images of plankton and associated environmental data are acquired by researchers around the globe using a variety of devices. Each individual data point provides information about biodiversity, functioning of aquatic foodwebs and ecosystem status of the related water body as well as its role in carbon sequestration. The Aquatic Life Foundation Project (AqQua) will leverage Europe’s first exascale HPC to build a foundational pelagic model training on billions of images acquired with a variety of devices. Fine-tuned for species classification, trait extraction and particulate organic carbon estimation, our foundation model will be distilled and deployed to the global community as a resource-efficient, easily usable tool. With this model we will establish global maps of species biodiversity, ecosystem status, and carbon flux at unprecedented accuracy and granularity, generating a fundamental understanding of marine and freshwater life in times of global change to aid decision making, in particular with respect to emerging ocean-bound carbon dioxide removal technologies.
AqQua is a Pilot Project in the Helmholtz Foundation Model Initiative.