K-PINN integrates Lattice-Boltzmann kinetics into a U-Net architecture to model droplet wettability on complex surfaces with L2 errors of 0.021-0.026, R² near 0.999, and mass conservation within 1.5% while enabling real-time inference.
Title resolution pending
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
2026 1verdicts
UNVERDICTED 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Lattice-Boltzmann-Driven Physics-Informed Neural Networks for Droplet Wettability on Rough Surfaces
K-PINN integrates Lattice-Boltzmann kinetics into a U-Net architecture to model droplet wettability on complex surfaces with L2 errors of 0.021-0.026, R² near 0.999, and mass conservation within 1.5% while enabling real-time inference.