DeepBedMap: A Super-Resolution Generative Adversarial Network for resolving the bed topography of Antarctica

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

• Wei Ji Leong | Antarctic Research Centre, Victoria University
• Tuesday 20 October 2020, 10:00-11:00
• https://us02web.zoom.us/j/89975312802?pwd=dkpvc0M3RGhtY1JOUm5Hc1dCNm9IZz09.

If you have a question about this talk, please contact Tudor Suciu.

A machine learning technique similar to the one used to enhance everyday photographs is applied to the problem of getting a better picture of Antarctica’s bed – that which is hidden beneath the ice. By taking hints from what satellites can observe at the ice surface, and training the model on high-resolution ground-truth data, the novel method is able to generate an image of the bed with better topographic characteristics than ordinary interpolation methods. The DeepBedMap model is based on an adapted Enhanced Super-Resolutionv Generative Adversarial Network architecture, chosen to minimize per-pixel elevation errors while producing realistic topography. The final product is a four times upsampled (250 m) bed elevation model of Antarctica that can be used by scientists running fine scale ice sheet models relevant for predicting future sea level trends.

Zoom link

Meeting ID: 899 7531 2802

Passcode: 945323

This talk is part of the AI4ER Seminar Series series.

This talk is included in these lists:

• AI4ER Seminar Series
• Cambridge Centre for Data-Driven Discovery (C2D3)
• Cambridge talks
• Chris Davis' list
• Interested Talks
• Trust & Technology Initiative - interesting events
• bld31
• https://us02web.zoom.us/j/89975312802?pwd=dkpvc0M3RGhtY1JOUm5Hc1dCNm9IZz09
• ndk22's list
• ob366-ai4er
• rp587

Note that ex-directory lists are not shown.