A Variational Neural Network Approach for Glacier Modelling with Nonlinear Rheology

A Variational Neural Network Approach for Glacier Modelling with Nonlinear Rheology

Year:    2023

Author:    Tiangang Cui, Zhongjian Wang, Zhiwen Zhang

Communications in Computational Physics, Vol. 34 (2023), Iss. 4 : pp. 934–954

Abstract

We propose a mesh-free method to solve the full Stokes equation for modeling the glacier dynamics with nonlinear rheology. Inspired by the Deep-Ritz method proposed in [13], we first formulate the solution to the non-Newtonian Stokes equation as the minimizer of a variational problem with boundary constraints. Then, we approximate its solution space by a deep neural network. The loss function for training the neural network is a relaxed version of the variational form, in which penalty terms are used to present soft constraints due to mixed boundary conditions. Instead of introducing mesh grids or basis functions to evaluate the loss function, our method only requires uniform sampling from the physical domain and boundaries. Furthermore, we introduce a re-normalization technique in the neural network to address the significant variation in the scaling of real-world problems. Finally, we illustrate the performance of our method by several numerical experiments, including a 2D model with the analytical solution, the Arolla glacier model with realistic scaling and a 3D model with periodic boundary conditions. Numerical results show that our proposed method is efficient in solving the non-Newtonian mechanics arising from glacier modeling with nonlinear rheology.

You do not have full access to this article.

Already a Subscriber? Sign in as an individual or via your institution

Journal Article Details

Publisher Name:    Global Science Press

Language:    English

DOI:    https://doi.org/10.4208/cicp.OA-2022-0272

Communications in Computational Physics, Vol. 34 (2023), Iss. 4 : pp. 934–954

Published online:    2023-01

AMS Subject Headings:    Global Science Press

Copyright:    COPYRIGHT: © Global Science Press

Pages:    21

Keywords:    Deep learning method variational problems mesh-free method non-Newtonian mechanics nonlinear rheology glacier modelling.

Author Details

Tiangang Cui

Zhongjian Wang

Zhiwen Zhang

  1. Forming Terrains by Glacial Erosion

    Cordonnier, Guillaume | Jouvet, Guillaume | Peytavie, Adrien | Braun, Jean | Cani, Marie-Paule | Benes, Bedrich | Galin, Eric | Guérin, Eric | Gain, James

    ACM Transactions on Graphics, Vol. 42 (2023), Iss. 4 P.1

    https://doi.org/10.1145/3592422 [Citations: 11]
  2. Solving nonconvex energy minimization problems in martensitic phase transitions with a mesh-free deep learning approach

    Chen, Xiaoli | Rosakis, Phoebus | Wu, Zhizhang | Zhang, Zhiwen

    Computer Methods in Applied Mechanics and Engineering, Vol. 416 (2023), Iss. P.116384

    https://doi.org/10.1016/j.cma.2023.116384 [Citations: 0]