arXiv · 2611.12275
SimpFlow: Transferable Pretraining for Fluid Dynamics via Simplified Physics
Abstract
Neural surrogates enable rapid fluid simulation, but learning across diverse three-dimensional (3D) geometries requires costly computational fluid dynamics (CFD) labels. We introduce SimpFlow, a pretraining approach that generates supervision from simplified physics on unlabeled geometry libraries. A source-panel potential-flow solver generates velocity and pressure fields for approximately 9,000 3D geometries, capturing geometry-induced acceleration, stagnation, and suction while omitting viscosity and separated wakes. The solver imports only a surface mesh and reuses precomputed velocity fields across inflow directions, enabling inexpensive label generation. In our benchmark, amortized labeling takes 0.111 s per example using four CPU threads. We pretrain a neural surrogate on these labels and fine-tune it on independent CFD datasets. Across five flow tasks, SimpFlow improves over training from scratch in all 24 task-budget settings. With fine-tuning fixed at 200 epochs, interpolation indicates that SimpFlow requires 35-68% fewer CFD training cases to match the error of scratch models trained at each task's largest data budget. These results demonstrate that simplified physical solutions can provide transferable supervision, offering a practical way to reduce the high-fidelity data requirements of fluid surrogates.
Explore related subjects
Keep this discovery
Explore connections, maps & timelines
Ruijie Li, Tianbai Xiao. 2026-11-09. SimpFlow: Transferable Pretraining for Fluid Dynamics via Simplified Physics. https://searcharxiv.com/abs/2611.12275
Citations retain the original authors and DOI and include this site’s record URL. If this discovery service contributed to your research, you can also cite Searcharxiv by Indiciae: BibTeX · RIS.