BayesTBNNLite: Bayesian tensor-basis neural network corrections for RANS turbulence models
The reproducible core of a study of Bayesian tensor-basis neural network corrections for RANS turbulence closures, with epistemic and aleatoric uncertainty propagated through the CFD solver. Contains the training dataset for six separated flows (periodic hill, curved backward-facing step, three parameterized hills and the NASA wall-mounted hump), the code that trains the scalar and anisotropy correction models, the four trained checkpoints, the OpenFOAM cases with meshes, and the published propagated statistics for comparison against a reproduction. Has no private dependencies: everything except the CFD runs from a clone and the supplied cond
Resource information
- Format
- zip
- Original repository
- 22021141
- DOI
- 10.5281/zenodo.22021141
- Credit basis
- Creators in Zenodo record metadata
- Access
- Open files available from the original Zenodo deposit
- Last checked
- Nov 5, 2026
- License
- mit-license
- Last record update
- Nov 5, 2026
About this resource
The reproducible core of a study of Bayesian tensor-basis neural network corrections for RANS turbulence closures, with epistemic and aleatoric uncertainty propagated through the CFD solver. Contains the training dataset for six separated flows (periodic hill, curved backward-facing step, three parameterized hills and the NASA wall-mounted hump), the code that trains the scalar and anisotropy correction models, the four trained checkpoints, the OpenFOAM cases with meshes, and the published propagated statistics for comparison against a reproduction. Has no private dependencies: everything except the CFD runs from a clone and the supplied conda environment.