Physics and Data Driven Transformer-Mamba Framework for Flow Field

Abstract:While deep learning accelerates expensive partial differential equation solving in computational fluid dynamics (CFD), existing methods like PINNs and FNOs often struggle with generalization, noise robustness, and physical consistency. We introduce the Transformer-Mamba for Flow Field (TM4FF) framework, a physics-constrained operator learning model with three key innovations: a Residual Wavelet Mamba (RWM) layer for feature denoising, a Transformer-based attention mechanism for enhanced feature fusion, and a physics-informed loss using Fourier derivatives to enforce the Navier-Stokes equations. Experiments on four CFD datasets show TM4FF achieves high accuracy and robust generalization across varying flow conditions.

Corrected version of our ICASSP'26 paper: Corrected seven Dam/MISSFormer metrics in Table 1 that were mistakenly estimated using the MSE(u) ratio. The conclusions remain unchanged

Machine Learning (cs.LG)

arXiv:2609.29087 [cs.LG]

(or arXiv:2609.29087v1 [cs.LG] for this version)

https://doi.org/10.48550/arXiv.2609.29087 arXiv-issued DOI via DataCite (pending registration)

https://doi.org/10.1109/ICASSP55912.2026.11460626 DOI(s) linking to related resources