AI RESEARCH
Adapting Automotive Aerodynamics Surrogates to New Vehicle Families via Transfer Learning
arXiv CS.LG
•
ArXi:2605.27968v1 Announce Type: cross Deploying Scientific Machine Learning surrogates in industrial CFD workflows requires adapting pretrained models to new vehicle families without large datasets; yet whether geometric representations learned by a geometry encoder transfer to topologically distinct shapes remains unvalidated. We address this through leave-one-family-out experiments on a 61.47M-parameter Transformer surrogate (AB-UPT) pretrained on four vehicle families (411 external aerodynamics cases) and adapted to the held-out fifth with only 20 samples.