ARTIFICIAL INTELLIGENCE FOR ICE SHELVES

This projects aims to develop the first EO-driven, AI system for predicting Antarctic ice shelf calving. Ice shelf instability is one of the most critical open questions in polar science, due to its capacity to drive rapid sea level change at - and beyond - current high-end climate projections. Yet forecasting future instability is notoriously difficult because of the complex, non-linear forcing mechanisms controlling an ice shelf’s response, including calving at the ice margin. As a result, the timescales for ice shelf collapse forms one of the largest uncertainties in modelling future sea level scenarios.

Our model of iceberg calving will act as a valuable first step towards addressing this uncertainty by improving our scientific understanding of - and ability to model - a process that contributes very strongly to ice shelf instability. Our project is designed with the long-term vision of incorporating our data-model framework into a future digital twin of Antarctica. This opens up the significant opportunity for future work to apply our model to ‘what if?’ scenarios and, ultimately, to inform downstream models, such as ocean circulation models, in a coupling between earth system components.

  Project Results