Neural-operator element method: Efficient and scalable finite element method enabled by reusable neural operators

TL;DR

The paper introduces NOEM, a hybrid finite element method that combines neural operators with traditional FEM to enable efficient, scalable, and reusable PDE solutions without dense meshing.

Contribution

It presents a novel neural-operator element method that integrates neural operators into FEM, reducing computational costs and enhancing reusability for complex PDE simulations.

Findings

NOEM achieves high accuracy in nonlinear PDEs.

It significantly reduces computational costs compared to traditional FEM.

The method scales well to complex geometries and multiscale problems.

Abstract

The finite element method (FEM) is a well-established numerical method for solving partial differential equations (PDEs). However, its mesh-based nature gives rise to substantial computational costs, especially for complex multiscale simulations. Emerging machine learning-based methods (e.g., neural operators) provide data-driven solutions to PDEs, yet they present challenges, including high training cost and low model reusability. Here, we propose the neural-operator element method (NOEM) by synergistically combining FEM with operator learning to address these challenges. NOEM leverages neural operators (NOs) to simulate subdomains where a large number of finite elements would be required if FEM was used. In each subdomain, an NO is used to build a single element, namely a neural-operator element (NOE). NOEs are then integrated with standard finite elements to represent the entire solution through the variational framework. Thereby, NOEM does not necessitate dense meshing and offers efficient simulations. We demonstrate the accuracy, efficiency, and scalability of NOEM by performing extensive and systematic numerical experiments, including nonlinear PDEs, multiscale problems, PDEs on complex geometries, and discontinuous coefficient fields.