A new fluid flow approximation method using a vision transformer and a U-shaped convolutional neural network

Numerical simulation of fluids is important in modeling a variety physical phenomena, such as weather, climate, aerodynamics, and plasma physics. The Navier–Stokes equations are commonly used to describe fluids, but solving them at large scale can be computationally expensive, particularly when it comes resolving small spatiotemporal features. This trade-off between accuracy tractability challenging. In this paper, we propose novel artificial intelligence-based method for improving fluid flow approximations computational dynamics (CFD) using deep learning (DL). Our method, called CFDformer, surrogate model that handle both local global features CFD input data. It also able adjust boundary conditions incorporate additional conditions, velocity pressure. Importantly, CFDformer performs well under different velocities pressures outside the flows was trained on. Through comprehensive experiments comparisons, demonstrate outperforms other baseline DL models, including U-shaped convolutional neural network (U-Net) TransUNet models.