Physics-constrained ML with a fractal prior outperforms purely data-driven models for subgrid interfacial area density in corrugation regimes of multiphase flows but shows no gain in fragmentation regimes.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
physics.comp-ph 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Learning subgrid interfacial area in two-phase flows with regime-dependent inductive biases
Physics-constrained ML with a fractal prior outperforms purely data-driven models for subgrid interfacial area density in corrugation regimes of multiphase flows but shows no gain in fragmentation regimes.