MAgNET: A graph U-Net architecture for mesh-based simulations

• DOI: 10.1016/j.engappai.2024.108055
• Publication Date: 2024-02-26T17:40:51Z
• Authors: Saurabh Deshpande; Stéphane P.A. Bordas; Jakub Lengiewicz
• Keywords: FOS: Computer and information sciences; Computer Science - Machine Learning; : Multidisciplinary, general & others [C99] [Engineering, computing & technology]; 0211 other engineering and technologies; 02 engineering and technology; Machine Learning (cs.LG); : Multidisciplinaire, généralités & autres [C99] [Ingénierie, informatique & technologie]; Computational Engineering, Finance, and Science (cs.CE); 03 medical and health sciences; 0302 clinical medicine; 0202 electrical engineering, electronic engineering, information engineering; Computer Science - Computational Engineering, Finance, and Science

In many cutting-edge applications, high-fidelity computational models prove to be too slow for practical use and are therefore replaced by much faster surrogate models. Recently, deep learning techniques have increasingly been utilized to accelerate such predictions. To enable learning on large-dimensional and complex data, specific neural network architectures have been developed, including convolutional and graph neural networks. In this work, we present a novel encoder-decoder geometric deep learning framework called MAgNET, which extends the well-known convolutional neural networks to accommodate arbitrary graph-structured data. MAgNET consists of innovative Multichannel Aggregation (MAg) layers and graph pooling/unpooling layers, forming a graph U-Net architecture that is analogous to convolutional U-Nets. We demonstrate the predictive capabilities of MAgNET in surrogate modeling for non-linear finite element simulations in the mechanics of solids.