Graph Neural Networks for Emulation of Finite-Element Ice Dynamics in Greenland and Antarctic Ice Sheets
This provides a faster emulation method for ice sheet modeling, which is incremental as it builds on existing graph neural network approaches.
The study tackled the computational inefficiency of finite-element ice sheet dynamics models by using an equivariant graph convolutional network (EGCN) as an emulator, achieving 260 times faster computation for Helheim Glacier and 44 times faster for Pine Island Glacier while maintaining accuracy.
Although numerical models provide accurate solutions for ice sheet dynamics based on physics laws, they accompany intensified computational demands to solve partial differential equations. In recent years, convolutional neural networks (CNNs) have been widely used as statistical emulators for those numerical models. However, since CNNs operate on regular grids, they cannot represent the refined meshes and computational efficiency of finite-element numerical models. Therefore, instead of CNNs, this study adopts an equivariant graph convolutional network (EGCN) as an emulator for the ice sheet dynamics modeling. EGCN reproduces ice thickness and velocity changes in the Helheim Glacier, Greenland, and Pine Island Glacier, Antarctica, with 260 times and 44 times faster computation time, respectively. Compared to the traditional CNN and graph convolutional network, EGCN shows outstanding accuracy in thickness prediction near fast ice streams by preserving the equivariance to the translation and rotation of graphs.