attention u-net 1complex geometries 1fluid dynamics prediction 1graph neural networks 1multi-scale features 1
From the 1 of 3 linked papers with an AI index.
3 papers
cs.LG2026
A multi-scale feature enhanced graph neural network for fluid dynamics prediction in complex geometries
Li Xiao, Tianyu Li, Yiye Zou +2
The paper introduces ME-GNN, a multi‑scale feature enhanced graph neural network that combines two‑step message passing, an Attention U‑Net, and K‑hop sampling to predict fluid flo…
physics.flu-dyn2026
Optimize discrete loss with finite-difference physics constraint and time-stepping for PDE solving
Yali Luo, Yiye Zou, Heng Zhang +4
Computational Fluid Dynamics (CFD) is an important approach for analyzing flow phenomena and predicting engineering-relevant quantities. The governing physics is formulated as part…
cs.LG2024
Finite-difference-informed graph network for solving steady-state incompressible flows on block-structured grids
Yiye Zou, Tianyu Li, Lin Lu +4
Advances in deep learning have enabled physics-informed neural networks to solve partial differential equations. Numerical differentiation using the finite-difference (FD) method i…