
FN
Favour Nerrise, Julian Busch, Gurpreet Singh Hora, Martin Sipka, Danielle C. Maddix, Georgia Olympia Brikis
· 1 min read
ResearcharXiv cs.LG
Measuring and Improving Transfer of Neural Surrogates for Vehicle Aerodynamics
arXiv:2611.24843v1 Announce Type: new
Abstract: Neural surrogates for external vehicle aerodynamics are fast alternatives to physics-based computational fluid dynamics (CFD) simulations. Their foundational limitation is a lack of zero-shot generalization across vehicle classes, which results in an expensive, custom training campaign for each new vehicle design. Similar to pretrained models in other fields, a pretrained surrogate should adapt to a new vehicle class using only a few simulations and stay accurate on its pretraining domain. No prior study has systematically tested this transfer behavior. We conduct a large-scale, controlled benchmarking study on five DrivAerML-pretrained surrogates across four independent target datasets. These datasets differ from the source in geometry, CFD solver, turbulence model, and flow conditions. We find that fine-tuning these surrogates outperforms training from scratch in fewer than half of the comparisons and lowers the accuracy of the surrogate on its source dataset. We introduce GeoReplay, a geometry- and gradient-aligned source replay that keeps source simulations resembling the target in training and applies their updates only when they agree with the target gradient. A risk bound separates geometric coverage from differences in the simulated physics, and we prove that every sufficiently small GeoReplay step decreases the target training objective. GeoReplay lowers the source error of fine-tuning in 77 of 80 settings and matches its target accuracy.
Original source
This story was published by arXiv cs.LG and written by Favour Nerrise, Julian Busch, Gurpreet Singh Hora, Martin Sipka, Danielle C. Maddix, Georgia Olympia Brikis. SyncAI.news shows a preview; the complete article is on the publisher's site.
Read the full story on arxiv.org


