A multi-horizon graph neural network emulator jointly predicts state increments for ice thickness and velocities at several lead times and shows higher long-range accuracy and stability than autoregressive or direct baselines on Pine Island Glacier simulations.
Greenland and Antarctica Ice Sheet Mass Changes and Effects on Global Sea Level
2 Pith papers cite this work, alongside 36 external citations. Polarity classification is still indexing.
2
Pith papers citing it
36
external citations · Crossref
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 2years
2026 2roles
background 1polarities
background 1representative citing papers
Adding MAR climate-model features plus a multi-branch GraphSAGE/temporal-convolution design with adaptive fusion reduces deep-ice-layer thickness RMSE by 21.01% over a no-knowledge multi-branch baseline on the SRED Greenland dataset.
citing papers explorer
-
From Short Histories to Long Futures: Horizon-Aware Graph Neural Networks for Long Horizon Forecasting
A multi-horizon graph neural network emulator jointly predicts state increments for ice thickness and velocities at several lead times and shows higher long-range accuracy and stability than autoregressive or direct baselines on Pine Island Glacier simulations.
-
K-STEMIT: Knowledge-Informed Spatio-Temporal Efficient Multi-Branch Graph Neural Network for Subsurface Stratigraphy Thickness Estimation from Radar Data
Adding MAR climate-model features plus a multi-branch GraphSAGE/temporal-convolution design with adaptive fusion reduces deep-ice-layer thickness RMSE by 21.01% over a no-knowledge multi-branch baseline on the SRED Greenland dataset.