Computational fluid dynamics iteration driven by data

Data-driven approaches have achieved remarkable success in different applications, however, their use in solving PDE has only recently emerged. Herein, we present the potential fluid method, which uses existing data to nest physical meanings into mathematical iterative processes. Potential fluid method is suitable for PDE, such as CFD problems, including Burgers? equation. Potential fluid method can iteratively determine the steady-state space distribution of PDE. For mathematical reasons, we compare the potential fluid method with the finite difference method and give a detailed explanation.