<ul><li>Neural operators have gained popularity in solving partial differential equations (PDEs) due to their ability to capture complex mappings in function spaces over complex domains.</li><li>The data requirements of neural operators limit their widespread use and transferability to new geometries.</li><li>To overcome this issue, a local-to-global framework called operator learning with domain decomposition is proposed for solving PDEs on arbitrary geometries.</li><li>The framework utilizes an iterative scheme called Schwarz Neural Inference (SNI) to solve local problems with neural operators and stitch local solutions to construct a global solution.</li></ul>

Operator Learning with Domain Decomposition for Geometry Generalization in PDE Solving

Discover more