This repository contains code from my Master's research internship, co-supervised at ISIR and LOCEAN labs (Sorbonne Université). Remote sensing provides essential data for monitoring ocean color and phytoplankton, which are important indicators of marine ecosystem health. However, missing data is a common issue in these observations, and addressing it is necessary to gain a complete understanding of ocean dynamics.
This project presents a transformer-based model designed to impute missing values in variables such as sea surface temperature, chlorophyll-a, and phytoplankton size classes. The model captures spatial, temporal, and multivariate correlations in 3D oceanographic data using self-attention mechanisms. The ability to handle sequences and multivariate data makes this approach a promising tool for oceanographic research.
You can find the full report and presentation slides for further details.