Hybrid FNO-LBM accelerates porous media flow convergence by up to 70% via neural initialization and stabilizes unsteady simulations through embedded FNO rollouts, allowing small models to match larger ones in accuracy.
Chen, Gary D
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
years
2026 2verdicts
UNVERDICTED 2roles
background 2polarities
background 2representative citing papers
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.
citing papers explorer
-
Hybrid Fourier Neural Operator-Lattice Boltzmann Method
Hybrid FNO-LBM accelerates porous media flow convergence by up to 70% via neural initialization and stabilizes unsteady simulations through embedded FNO rollouts, allowing small models to match larger ones in accuracy.
-
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.