SIAM Journal on Scientific Computing · 2023 · 11 citations · 33 references
Natural SciencesMathematicsComputational Fluid DynamicsDifferential EquationsFluid DynamicsNavier-stokes EquationsNumerical AnalysisPartial Differential EquationsPrincipal Component AnalysisUnsupervised LearningInitial Guess StrategiesNonlinear Equation SystemsNonlinear Partial Differential EquationsNonlinear PreconditioningNonlinear SystemsPreconditioningPreconditioning TechniquesSubspace Learning
.Nonlinearly preconditioned inexact Newton methods have been applied successfully for some difficult nonlinear systems of algebraic equations arising from the discretization of partial differential equations. The preconditioning step involves identifying and balancing the nonlinearities in the system. One of the challenging tasks when applying the methods is to accurately and efficiently identify the unbalanced nonlinearities. In this work, we propose an unsupervised learning strategy based on the classical principal component analysis that learns the bad behavior of a Newton solver in the nonlinear residual subspace of a training problem. A new initial guess is produced by the nonlinear preconditioner where a projected low dimensional Jacobian system corresponding to the slow subspace of the current residuals is solved for the Newton correction vector. Numerical experiments for high Reynolds number incompressible flow problems show that the proposed method is more robust and efficient compared with existing nonlinear solvers.Keywordsinexact Newtonlearning-based nonlinear preconditioningprincipal component analysisnonlinear system of algebraic equationsincompressible Navier–Stokes equationsMSC codes49M1565Y0565M5576D05
33
Maziar Raissi, Paris Perdikaris, George Em Karniadakis · Journal of Computational Physics · 2018 · 16.9K citations · Full text
Machine Learning for Fluid Mechanics
Annual Review of Fluid Mechanics · 2019 · 2.6K citations · Full text