Fourier filter-based physics- information convolutional recurrent network for 2D incompressible flow

Physics-informed convolutional recurrent network (PhyCRNet) can solve partial differential equations without labeled data by encoding physics constraints into the loss function. However, finite-difference filter makes solution of 2D incompressible flow challenging. Hence, this paper proposes a Fourier filter-based physics-informed convolution (named PhyCRNet), which replaces in PhyCRNet with to problem. The suggested improves accuracy derivatives, solves inverse Laplacian operator, and has similar generalization ability due inheriting framework PhyCRNet. Four examples, including viscous Burger, FitzHugh–Nagumo RD, vorticity two-dimensional Navier- Stokes (N-S) equations, validate correctness reliability proposed