Neural enrichment finite element method: A hybrid framework for problems with strong oscillations or interface problems
For computational scientists solving PDEs with oscillations or interfaces, NEFEM offers a hybrid method that reduces computational cost without needing problem-specific enrichment functions.
The Neural Enrichment Finite Element Method (NEFEM) is proposed for problems with strong oscillations or interface problems, reducing required degrees of freedom while requiring minimal a priori knowledge for enrichment functions. Theoretical error bounds and optimal convergence are proven, with numerical validation.
We propose a hybrid method, the Neural Enrichment Finite Element Method (NEFEM), designed for problems involving strong oscillations or interface problems with weak discontinuities. This method is based on the stable generalized finite element method (SGFEM) framework, wherein neural networks (NNs) are introduced as enrichment functions for adaptivity, and the Ritz functional is applied for the training process. This works makes two main contributions. First, the method constructs local subspaces with superior approximation properties, significantly reducing the required number of degrees of freedom (DoFs). Second, minimal \emph{a priori} knowledge is required to define enrichment functions, as the NNs evolve heuristically during training. Furthermore, for smooth problems, we provide a residual-based error estimator and prove both its reliability and efficiency. For interface problems, a theoretical analysis on the optimal convergence of the SGFEM is studied, notably without imposing additional regularity assumptions. These analytic results guide the network architecture design and training strategies. The performance and effectiveness of the proposed method is validated through several numerical experiments.