K-Means cluster-weighted training cuts average MSE 34% and lifts R² from 0.54 to 0.80 for a 3D CNN predicting Reynolds stresses on StellarBox quiet-Sun data.
Physics-informed machine learning for modeling turbulence in supernovae,
1 Pith paper cite this work, alongside 12 external citations. Polarity classification is still indexing.
1
Pith paper citing it
12
external citations · OpenAlex
fields
astro-ph.SR 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Cluster-Weighted Training of Deep Surrogate Models for Subgrid Turbulent Transport
K-Means cluster-weighted training cuts average MSE 34% and lifts R² from 0.54 to 0.80 for a 3D CNN predicting Reynolds stresses on StellarBox quiet-Sun data.