After 4 decades of slight expansion, Antarctic sea ice extent has experienced several record minima in the last few years, culminating in the largest negative anomaly on record in the austral winter of 2023.

Land use and land cover change contribute significantly to anthropogenic CO2 emissions and biodiversity loss. However, current inventory-based statistics miss year-to-year land changes, preventing a comprehensive global understanding. Earth observation by satellite provides valuable information for mapping global annual changes at the pixel level.

The presentation is proposed under the back to school scheme of the European Commission which encourages EC staff to go back to the schools or Universities which educated them to talk about European policies.

Physics-informed neural networks (PINNs) represent a class of versatile function approximators capable of incorporating the physics principles, e.g., partial differential equations (PDEs), governing a specific dataset within the learning process.

In order to take better care of our agricultural soils, we need to be able to monitor them. Earth observation could be a piece in the puzzle that is soil monitoring.  Therefore, in my research I investigate how we can use satellite observations to learn about the organic carbon content in soils. I will explain why this could work and why that would be valuable.