I study the future of the Antarctic Ice Sheet and how much it will contribute to global sea-level rise. My work combines computer models of ice flow with machine learning to make these predictions faster and more reliable.

I'm particularly interested in using deep learning to emulate physical models: training neural networks to reproduce the behaviour of detailed ice-flow simulations at a fraction of the computational cost. This makes it possible to explore many more scenarios and to better quantify the uncertainty in projections of ice loss.

More broadly, my research spans the dynamics of ice sheets, ice shelves and ice streams: from how ocean tides modulate ice flow on timescales of hours and days, to the long-term response of the ice sheet to a changing climate over centuries and possible future tipping point behaviour.