Machine learning can be used for processing Sentinel-3 Ocean Colour data. A neural network approach underpins the atmospheric correction and estimation of ocean parameters – such as chlorophyll and TSM – in complex waters for Sentinel-3. This deals with the fundamental problem of how to extract useful information from a complex signal. Being able to tell the difference between chlorophyll and sediment is fundamentally important for ocean researchers using EO data. It is very difficult to be able to tell the difference between sediment and chlorophyll from satellite images – yet the difference can be crucial for monitoring the marine environment.

Identifying chlorophyll is important, because chlorophyll plays the role in the ocean that grass plays on land. Chlorophyll is microscopic individual floating cells, which play a key role in the marine food chain. It also removes CO2 from the ocean.

Using ML to solve this problem makes marine data as a whole more robust – and researchers can be more certain about the results they are getting. In coastal water round the UK there is a lot of sediment, so researchers need to be careful that what they think they are seeing is what they are actually seeing – this ML becomes a key part of their workflow.

Featured Educator

• Lauren Biermann

‍