Fluids You Can Trust: Property-Preserving Operator Learning for Incompressible Flows

ArXi:2602.15472v3 Announce Type: replace-cross We present a novel property-preserving kernel-based operator learning method for incompressible flows governed by the incompressible Navier--Stokes equations. Traditional numerical solvers incur significant computational costs to respect incompressibility. Operator learning offers efficient surrogate models, but current neural operators fail to exactly enforce physical properties such as incompressibility, periodicity, and turbulence.