Discretizationnet: a machine-learning based solver for Navier-Stokes equations using finite volume discretization

DOI10.1016/j.cma.2021.113722zbMath1506.76115arXiv2005.08357MaRDI QIDQ2021855

Rishikesh Ranade, Chris Hill, Jay Pathak

Publication date: 27 April 2021

Published in: Computer Methods in Applied Mechanics and Engineering (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2005.08357

zbMATH Keywords

partial differential equations; machine learning; discretization methods; physics-informed learning

Mathematics Subject Classification ID

76D05: Navier-Stokes equations for incompressible viscous fluids

76M12: Finite volume methods applied to problems in fluid mechanics

65N08: Finite volume methods for boundary value problems involving PDEs

Related Items

DiscretizationNet

Uses Software

• FLUENT
• Keras
• DiffSharp
• MeshCNN
• DeepXDE
• PhyGeoNet
• PPINN
• VarNet
• D3M
• NSFnets
• hp-VPINNs