Conference
Open access
Sep 2026
UNOP: Physics-Constrained Unsupervised Neural Operator for Long-Horizon PDE Learning on Generalized Geometries
This work presents a physics-constrained un-supervised neural operator for long-horizon PDE learning on generalized geometries (UNOP), which replaces differential constraints with integral consistency for stable, label-free learning.
Xin-Rui Cheng, Tian-Qi Zhao, Zhao-Dong Zhang et al.
· Proceedings of the Thirty-Fi... · 0 citations