An $r$-adaptive finite element method using neural networks for parametric self-adjoint elliptic problem

Abstract

This work proposes an $r$-adaptive finite element method (FEM) using neural networks (NNs). The method employs the Ritz energy functional as the loss function, currently limiting its applicability to symmetric and coercive problems, such as those arising from self-adjoint elliptic problems. The objective of the NN optimization is to determine the mesh node locations. For simplicity in two-dimensional problems, these locations are assumed to form a tensor product structure. The method is designed to solve parametric partial differential equations (PDEs). For each PDE parameter instance, the optimal $r$-adapted mesh generated by the NN is then solved with a standard FEM. The construction of FEM matrices and load vectors is implemented such that their derivatives with respect to mesh node locations, required for NN training, can be efficiently computed using automatic differentiation. However, the linear equation solver does not need to be differentiable, enabling the use of efficient, readily available `out-of-the-box' solvers. Consequently, the proposed approach retains the robustness and reliability guarantees of the FEM for each parameter instance, while the NN optimization adaptively adjusts the mesh node locations. The method's performance is demonstrated on parametric Poisson problems using one- and two-dimensional tensor product meshes.

References in corpus (10)

• hp-VPINNs: Variational Physics-Informed Neural Networks With Domain Decomposition
• Axioms of Adaptivity
• JAX-FEM: A differentiable GPU-accelerated 3D finite element solver for automatic inverse design and mechanistic data science
• Variational Physics Informed Neural Networks: the role of quadratures and test functions
• Finite element interpolated neural networks for solving forward and inverse problems
• On quadrature rules for solving Partial Differential Equations using Neural Networks
• A Deep Double Ritz Method (D${}^2$RM) for solving Partial Differential Equations using Neural Networks
• A framework for structural shape optimization based on automatic differentiation, the adjoint method and accelerated linear algebra
• Optimizing Variational Physics-Informed Neural Networks Using Least Squares
• Compatible finite element interpolated neural networks