Deep Learning-based surrogate models for parametrized PDEs: handling geometric variability through graph neural networks

no code implementations • 3 Aug 2023 • Nicola Rares Franco, Stefania Fresca, Filippo Tombari, Andrea Manzoni

We also assess, from a numerical standpoint, the importance of using GNNs, rather than classical dense deep neural networks, for the proposed framework.

Computational Efficiency valid