A residual- and realizability-filtered CFD-driven GEP framework reduces computational cost by 42.3 percent and non-realizable models from 58.4 percent to 1.7 percent for turbulence closure discovery in wake 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
CONDITIONAL 1representative citing papers
citing papers explorer
-
Realizability-Constrained Machine Learning for Turbulence Closures in Wake Flows
A residual- and realizability-filtered CFD-driven GEP framework reduces computational cost by 42.3 percent and non-realizable models from 58.4 percent to 1.7 percent for turbulence closure discovery in wake flows.