No AI summary available for this article.
Why It Matters
Pretraining a neural PDE surrogate can reduce the amount of new CFD data needed when geometry or modeled physics changes.
Provenance
Discovered via ArXiv and published by ArXiv.
Key Claims
Original description
Pretraining a neural PDE surrogate can reduce the amount of new CFD data needed when geometry or modeled physics changes. However, it remains unclear how different components of distribution shift affect this benefit. We pretrain a surrogate on 254,909 RANS solutions from one airfoil family and fine-tune it on a new family under two target settings with matched freestream ranges: the same Spalart-Allmaras (SA) modeling and SA with added $e^N$ transition modeling. At $N=1000$, the pretrained model matches the accuracy of a model trained from scratch on $3.25\times$ as many samples for the same-...
Discovered via ArXiv
Research papers and preprints from arXiv.
Publisher: arxiv.org
ID: http://arxiv.org/abs/2609.20814v1 · Indexed about 1 hour ago