Project: Improving capabilities to predict krill habitats to protect Southern Ocean ecosystems and carbon sinks
Supervisors: Dr Emma Cavan (Imperial), Dr Adam Sykulski (Imperial) and Dr André Victor Ribeiro Amaral (Southampton)
Project Description:
This project aims to significantly improve predictions of the distribution of Antarctic krill in the Southern Ocean, utilising a data-driven and machine learning approach to fuse heterogenous data sources across multiple scales. The Southern Ocean is one of the most important oceanic carbon sinks in the global oceans, with Antarctic krill playing a crucial role in driving carbon sequestration through their faecal pellets. At present, it is not possible to map the abundance and distribution of krill dynamically and remotely and the statistical challenge of doing this is significant. The data sources, while producing vast databases in isolation, are multiscale in nature and are complex to integrate in one prediction methodology due to their non-linear interactions. To overcome this, the project will implement state-of-the-art and recently developed methodologies in spatial machine learning, while also integrating ideas from classical spatio-temporal statistics. Overall, this project hopes to characterise how fishing and climate change may be impacting krill and therefore the carbon sink and wider Southern Ocean ecosystem.
