Bayesian neural networks correct RANS turbulence models via kinetic energy source terms and anisotropy tensors, improving velocity predictions on training flows but showing reduced accuracy and under-coverage on unseen separated flows.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
physics.flu-dyn 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Bayesian neural network correction of RANS turbulence models with uncertainty quantification in separated flows
Bayesian neural networks correct RANS turbulence models via kinetic energy source terms and anisotropy tensors, improving velocity predictions on training flows but showing reduced accuracy and under-coverage on unseen separated flows.