DeepTopoNet, a CNN with dynamic loss balancing, predicts subglacial bed elevation in Greenland, but its high accuracy is measured against BedMachine, the same map it is trained to fit.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
DeepTopoNet: A Framework for Subglacial Topography Estimation on the Greenland Ice Sheets
DeepTopoNet, a CNN with dynamic loss balancing, predicts subglacial bed elevation in Greenland, but its high accuracy is measured against BedMachine, the same map it is trained to fit.