Nudging enables a-priori training of stable neural network turbulence closures for LES that adapt to various numerical schemes without solver modifications or adjoints.
Bezgin, Aaron B
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2representative citing papers
PINNs fail on spurious solutions admitted by the residual loss; adaptive pseudo-time stepping with Jacobian-based step selection improves accuracy and robustness on PDE benchmarks.
citing papers explorer
-
Deep Learning of Solver-Aware Turbulence Closures from Nudged LES Dynamics
Nudging enables a-priori training of stable neural network turbulence closures for LES that adapt to various numerical schemes without solver modifications or adjoints.
-
When PINNs Go Wrong: Pseudo-Time Stepping Against Spurious Solutions
PINNs fail on spurious solutions admitted by the residual loss; adaptive pseudo-time stepping with Jacobian-based step selection improves accuracy and robustness on PDE benchmarks.