A physics-conditioned neural network with geometric and transformer components synthesizes complete ice-layer thickness from incomplete radar traces using a mask-aware loss, preserving observed values and improving downstream predictions.
Prediction of annual snow accumulation using a recurrent graph convolutional approach
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Physics-Conditioned Synthesis of Internal Ice-Layer Thickness for Incomplete Layer Traces
A physics-conditioned neural network with geometric and transformer components synthesizes complete ice-layer thickness from incomplete radar traces using a mask-aware loss, preserving observed values and improving downstream predictions.