NORi augments a Richardson number-dependent diffusivity and viscosity closure with neural ODEs trained a posteriori on LES data to parameterize ocean boundary layer entrainment, matching k-ε performance at OWS Papa and remaining stable in 100-year double-gyre runs despite 2-day training horizons.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
physics.ao-ph 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
NORi: An ML-Augmented Ocean Boundary Layer Parameterization
NORi augments a Richardson number-dependent diffusivity and viscosity closure with neural ODEs trained a posteriori on LES data to parameterize ocean boundary layer entrainment, matching k-ε performance at OWS Papa and remaining stable in 100-year double-gyre runs despite 2-day training horizons.