A vanilla PINN trained with six strategically placed velocity labels, or with approximate velocity labels, can predict 2D stirred-tank flow with roughly 2.5-3% error across most tested Reynolds numbers, far fewer labels than a supervised NN.
Physics Informed Neural Net- works for Modeling of 3D Flow-Thermal Problems with Sparse Domain Data
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CE 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Quantifying data needs in surrogate modeling for flow fields in two-dimensional stirred tanks with physics-informed neural networks
A vanilla PINN trained with six strategically placed velocity labels, or with approximate velocity labels, can predict 2D stirred-tank flow with roughly 2.5-3% error across most tested Reynolds numbers, far fewer labels than a supervised NN.