5 papers
Geometry-aware LegONet for PDE Learning on Arbitrary Domains
Jiahao Zhang, Yueqi Wang, Guang Lin
Learned PDE solvers often entangle governing operators with the geometry, boundary conditions, and discretization used for training. This limits reuse when the same physics is pose…
Generative Prior-Guided Neural Interface Reconstruction for 3D Electrical Impedance Tomography
Haibo Liu, Junqing Chen, Guang Lin
Reconstructing complex 3D interfaces from indirect measurements remains a grand challenge in scientific computing, particularly for ill-posed inverse problems like Electrical Imped…
LegONet: Plug-and-Play Structure-Preserving Neural Operator Blocks for Compositional PDE Learning
Jiahao Zhang, Yueqi Wang, Guang Lin
Learned PDE solvers are often trained as monolithic surrogates for a specific equation, boundary condition and discretization. This makes them difficult to reuse when mechanisms ch…
A POD-DeepONet Framework for Forward and Inverse Design of 2D Photonic Crystals
Yueqi Wang, Guanglian Li, Guang Lin
We develop a reduced-order operator-learning framework for forward and inverse band-structure design of two-dimensional photonic crystals with binary, pixel-based -symmetric u…
Reduced-Basis Deep Operator Learning for Parametric PDEs with Independently Varying Boundary and Source Data
Yueqi Wang, Guang Lin
Parametric PDEs power modern simulation, design, and digital-twin systems, yet their many-query workloads still hinge on repeatedly solving large finite-element systems. Existing o…