GLOBE
Learned Green's-function kernels from boundary faces
Paper title GLOBE: Accurate and Generalizable PDE Surrogates using Domain-Inspired Architectures and Equivariances
Paper arXiv 2511.15856PDF
Borrowed from boundary-element methods: the field at any point is a sum of learnable Green's-function-like kernels evaluated from every boundary face, with multi-scale branches, boundary-to-boundary communication layers and an explicit far-field decay. The model is translation, rotation, parity and units invariant.
- Data
- AirfRANS
Share on LinkedIn, X or Bluesky, or or .
Know related work that belongs here? Suggest a link
Something wrong on this page? Tell the editor