Metraipolis › archive › dc_e609cb355b47

Predictive Uncertainty for Neural CAE Surrogates — arXiv:2609.25430

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.25430
License (as archived)
CC0-1.0
Archived
2026-10-08T13:46:20.352Z
SHA-256 of the archived text
6a31cedfa4accdd3e4e4180c14f2829df0d53eefe2d2603255161bca83c35856
Stable URL of this page
https://metraipolis.com/documento/dc_e609cb355b47

How to cite

Predictive Uncertainty for Neural CAE Surrogates — arXiv:2609.25430 — arXiv (en), https://arxiv.org/abs/2609.25430 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e609cb355b47 (Metraipolis archive dc_e609cb355b47, sha256 6a31cedfa4accdd3e4e4180c14f2829df0d53eefe2d2603255161bca83c35856)
BibTeX
@misc{dce609cb355b47,
  title = {Predictive Uncertainty for Neural CAE Surrogates — arXiv:2609.25430},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.25430},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e609cb355b47; sha256 6a31cedfa4accdd3e4e4180c14f2829df0d53eefe2d2603255161bca83c35856},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.25430. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Neural surrogates can substantially accelerate computer-aided engineering (CAE) workflows, but their use in design requires uncertainty estimates that remain meaningful across varying geometries, spatial prediction fields, and engineering quantities of interest. We investigate how established uncertainty quantification (UQ) approaches behave when adapted to geometry-conditioned neural surrogates. We compare one closed-form and two sampling-based approaches-a Gaussian process (GP)-based method, concrete Monte Carlo (MC) dropout, and deep ensembles-and evaluate them on three large, industry-relevant CAE datasets for external aerodynamics and crash dynamics. We examine whether predicted uncertainties have credible magnitudes, identify locations with larger prediction errors, respond to unfamiliar inputs, and remain informative for derived engineering quantities. On the DrivAerStar dataset, where all three methods are compared, each generally assigns higher uncertainty to locations with larger prediction errors, and validation-based rescaling brings interval coverage close to nominal on a disjoint in-distribution test set. Results on AirFRANS and automotive crash also show useful error ranking and interval estimates, but the relative performance of the methods changes with the dataset and evaluation criterion. UQ methods and evaluation metrics should therefore be selected based on the intended downstream CAE decision.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-23 in cs.AI).
Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI); Probability (math.PR); Computational Physics (physics.comp-ph).
Pagina del lavoro: https://arxiv.org/abs/2609.25430 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-08T13:18:38.226Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-23?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).