A Hybrid Neural Network-Finite Element Method for the Viscous-Plastic Sea-Ice Model

TL;DR

This paper introduces a hybrid neural network-finite element method to efficiently simulate viscous-plastic sea-ice dynamics, significantly reducing computational costs while maintaining accuracy in capturing deformation features.

Contribution

It proposes a local neural network correction to coarse-mesh finite element solutions, enabling faster and accurate sea-ice modeling compared to traditional high-resolution simulations.

Findings

Achieves approximately 11 times lower computational cost with similar accuracy.

Accelerates the Newton solver by up to 10% using neural network corrections.

Enables coarse-mesh simulations to effectively capture fine-scale deformation features.

Abstract

We present an efficient hybrid Neural Network-Finite Element Method (NN-FEM) for solving the viscous-plastic (VP) sea-ice model. The VP model is widely used in climate simulations to represent large-scale sea-ice dynamics. However, the strong nonlinearity introduced by the material law makes VP solvers computationally expensive, with the cost per degree of freedom increasing rapidly under mesh refinement. High spatial resolution is particularly required to capture narrow deformation bands known as linear kinematic features in viscous-plastic models. To improve computational efficiency in simulating such fine-scale deformation features, we propose to enrich coarse-mesh finite element approximations with fine-scale corrections predicted by neural networks trained with high-resolution simulations. The neural network operates locally on small patches of grid elements, which is efficient due to its relatively small size and parallel applicability across grid patches. An advantage of this local approach is that it generalizes well to different right-hand sides and computational domains, since the network operates on small subregions rather than learning details tied to a specific choice of boundary conditions, forcing, or geometry. The numerical examples quantify the runtime and evaluate the error for this hybrid approach with respect to the simulation of sea-ice deformations. Applying the learned network correction enables coarser-grid simulations to achieve qualitatively similar accuracy at approximately 11 times lower computational cost relative to the high-resolution reference simulations. Moreover, the learned correction accelerates the Newton solver by up to 10% compared to runs without the correction at the same mesh resolution.