Turning complex data into clean stories, sharp plots, and smarter science.

I developed a deep learning approach that combines meteorology, wave dynamics, and river discharge to reconstruct and forecast suspended sediment dynamics, filling temporal data gaps and capturing complex, nonlinear relationships in coastal environments.

I downscaled IPCC climate projections to a local area of France and combined mechanistic modeling with advanced trend detection methods (Mann–Kendall and Hurst–Kolmogorov) to reliably assess how long‑term changes in irradiance, temperature, and other climate drivers will affect microalgal productivity and its role in coastal ecosystem dynamics.

Accounting for carbon and nutrients in rivers is essential for resolving carbon dioxide (CO₂) exchanges between the ocean and the atmosphere. In this study, I added the effect of present-day rivers to a pioneering global-ocean biogeochemistry model. This study highlights the challenge for global ocean numerical models to cover the complexity of the flow of water and carbon across the Land-to-Ocean Aquatic Continuum.

I developed an algorithm that fuses satellite, laboratory, and modeling data to create seamless, high‑fidelity geospatial fields, leveraging the strengths of each source to fill temporal gaps, reduce uncertainty, and deliver robust, actionable insights for coastal and marine environments.

I implemented a comprehensive Monte Carlo sensitivity analysis for benthic microalgae productivity, efficiently exploring multi‑dimensional parameter spaces and revealing key drivers, interactions, and thresholds that strengthened model parameterization and predictive skills.