A Sentinel-3 foundation model for ocean colour
This addresses the problem of sparse labeled data in ocean science for marine monitoring and climate research, representing an incremental application of existing foundation model concepts to a specific domain.
The researchers developed a Sentinel-3 foundation model using the Prithvi-EO Vision Transformer architecture, pre-trained on unlabeled ocean color data, and demonstrated its utility by fine-tuning it for chlorophyll concentration quantification and ocean primary production estimation, matching point observations while capturing detailed spatial patterns.
Artificial Intelligence (AI) Foundation models (FMs), pre-trained on massive unlabelled datasets, have the potential to drastically change AI applications in ocean science, where labelled data are often sparse and expensive to collect. In this work, we describe a new foundation model using the Prithvi-EO Vision Transformer architecture which has been pre-trained to reconstruct data from the Sentinel-3 Ocean and Land Colour Instrument (OLCI). We evaluate the model by fine-tuning on two downstream marine earth observation tasks. We first assess model performance compared to current baseline models used to quantify chlorophyll concentration. We then evaluate the FMs ability to refine remote sensing-based estimates of ocean primary production. Our results demonstrate the utility of self-trained FMs for marine monitoring, in particular for making use of small amounts of high quality labelled data and in capturing detailed spatial patterns of ocean colour whilst matching point observations. We conclude that this new generation of geospatial AI models has the potential to provide more robust, data-driven insights into ocean ecosystems and their role in global climate processes.