Parameterising melt at the base of Antarctic ice shelves with a feedforward neural network

Add to your list(s) Download to your calendar using vCal

• Clara Burgard, University of Grenoble Alpes
• Monday 16 January 2023, 14:00-15:00
• BAS Seminar Room 1;https://ukri.zoom.us/j/95564564065.

If you have a question about this talk, please contact Dr. Shenjie Zhou.

The largest uncertainty when projecting the Antarctic contribution to sea-level rise comes from the ocean-induced melt at the base of Antarctic ice shelves. Current physics-based parameterisations used to link the ocean temperature and salinity in front of ice shelves to the melt at their base struggle to accurately simulate basal melt patterns. We explore the potential of a deep feedforward neural network as a basal melt parameterisation. To do so, we train a neural network to emulate basal melt rates simulated by highly-resolved circum-Antarctic ocean simulations. We explore the influence of different input variables and show that the neural network struggles to generalise to ice-shelf geometries unseen during training, while it generalises better on timesteps unseen during training. This is work in progress and I am looking forward to discuss improvements and limitations of this approach.

This talk is part of the British Antarctic Survey - Polar Oceans seminar series series.

This talk is included in these lists:

• All Talks (aka the CURE list)
• BAS Seminar Room 1;https://ukri.zoom.us/j/95564564065
• Biology
• British Antarctic Survey
• Cambridge Environment
• Climate Science Seminars within Cambridge
• Featured lists
• Life Sciences
• Life Sciences
• ME Seminar
• Queens' College Politics Society
• School of Physical Sciences
• Talks related to atmosphere and ocean dynamics and climate science
• my_list
• ob366-ai4er
• other talks

Note that ex-directory lists are not shown.