Key Expoitable Results (KERs)

As the volume of accessible marine pelagic observations increases exponentially, incorporating diverse data types such as metagenomics and quantitative imaging, the need for standardized modelling frameworks becomes critical to predict biogeographic patterns in space and time and across the diverse range of emergent sampling methods. In response, we introduce CEPHALOPOD (Comprehensive Ensemble Pipeline for Habitat modelling Across Large-scale Ocean Pelagic Observation Datasets), a standardized, highly automated and flexible framework designed to integrate and analyse heterogeneous marine data for multi-species habitat modelling following best practices in the field. CEPHALOPOD is built on observational data from federating initiatives such as AtlantECO, OBIS, GBIF, associated with already existing statistical and machine learning methods that enable to extract and model information from heterogeneous, scarce and biased field observations. It is highly automated and follows explicit quality checks informing the user of the predictive accuracy and interpretability of the results. Here, we document our statistical ensemble modelling approach and then assess its strengths and limitations with a virtual ecologist approach. We show how our framework performs in reproducing a range of distributions from biased field samples. Our modelling framework serves as a foundation for the consistent generation of Essential Biodiversity and Ocean Variables (EBVs and EOVs) and carries the potential to significantly advance our comprehension of biodiversity and marine ecosystem functioning. Finally, it provides an unprecedented opportunity to foster collaborations in the field of marine science, sustainable ecological practices, and ultimately contribute to the preservation of global marine biodiversity.