DNN-MG: A Hybrid Neural Network/Finite Element Method with Applications to 3D Simulations of the Navier-Stokes Equations.
Nils MargenbergRobert JendersieChristian LessigThomas RichterPublished in: CoRR (2023)
Keyphrases
- finite element method
- navier stokes equations
- boundary conditions
- numerical simulations
- finite element
- numerical solution
- diffuse optical tomography
- temperature field
- boundary element method
- numerical methods
- theoretical analysis
- finite element model
- heat transfer
- shape from shading
- hybrid neural network
- neural network
- simulation model
- sufficient conditions
- training process
- finite difference method
- objective function