A neural network trained on density fluctuations learns generalized transport coefficients that reproduce Shakhov and DSMC spectra up to Knudsen number 10, extending spectral closure hydrodynamics beyond its critical wave number.
As a further illustration of the optimality of the spec- trally closed hydrodynamics, we compute the time evolu- tion of density and temperature directly
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
physics.flu-dyn 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Learning the Optimal Hydrodynamic Closure
A neural network trained on density fluctuations learns generalized transport coefficients that reproduce Shakhov and DSMC spectra up to Knudsen number 10, extending spectral closure hydrodynamics beyond its critical wave number.