An attention-enhanced FNO+U-Net predicts mixed-GMsFEM multiscale bases; a two-grid preconditioner then solves the assembled Darcy system more accurately than pure learning baselines and faster offline than classical GMsFEM.
Prediction of multiscale features using deep learning-based preconditioner-solver architecture for darcy equation in high-contrast media
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CE 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Applying Two-Grid Preconditioner for Subsurface Flow Simulation using Attention-enhanced Hybrid Network to Accelerate Multiscale Discretization in High-contrast Media
An attention-enhanced FNO+U-Net predicts mixed-GMsFEM multiscale bases; a two-grid preconditioner then solves the assembled Darcy system more accurately than pure learning baselines and faster offline than classical GMsFEM.