NeuroForge: Self-Auditing Neural CFD Surrogates with Calibrated Physics-Residual Trust

[2607.10333] NeuroForge: Self-Auditing Neural CFD Surrogates with Calibrated Physics-Residual Trust Skip to main content Search Submit Donate Log in Physics > Fluid Dynamics arXiv:2607.10333 (physics) [Submitted on 11 Jul 2026 ( v1 ), last revised 25 Aug 2026 (this version, v3)] Title: NeuroForge: Self-Auditing Neural CFD Surrogates with Calibrated Physics-Residual Trust Authors: Ali Jabbary (Urmia University), Kasra Ghanavati (University of Greenwich) View PDF HTML (experimental) Abstract: Machine-learning surrogates for computational fluid dynamics (CFD) predict steady flow fields far faster than classical solvers, but emit a single field with no built-in way to know whether to trust it -- especially out of distribution. We make the surrogate audit itself against the governing physics: we compute the discretised steady-state Reynolds-averaged (RANS) residual of the prediction and ask what jobs it can do. Our central finding is a clean two-way dissociation: the physics residual is a reliable, backbone-robust trust signal (it tells you where the prediction is wrong) but a poor correction objective (it does not tell you how to fix it). As a trust signal, the residual's per-case rank correlation with field error is consistently positive across three architecturally distinct backbones and a second dataset of laminar bluff bodies; it flags the worst-decile cases with AUROC $\approx 0.9$, and a distribution-free split-conformal layer attains its target coverage. As a correction objective, the residual fails: reducing it does not reduce field error. The monotone-residual acceptance gate built on it, by contrast, does help. Separately, a learned deep-equilibrium corrector trained toward ground truth lowers volume-field error on a state-of-the-art backbone; a controlled ablation that removes the residual input matches this gain, so the improvement comes from the learned correction, not from conditioning on the residual. The contribution is a self-auditing, calibrated trust layer, the residual's two roles (trust signal yes, correction objective no), and the learned correction it accompanies, demonstrated on a competitive surrogate and released as the open-source neuroforge-cfd package. Comments: 31 pages, 10 figures, 9 tables. v3 corrects v2's claim that the eddy-viscosity channel is effectively unlearned: measured, it is learned (R^2 0.996 grid backbone, 0.67-0.70 MeshGraphNet) and supplies 84% of nu_eff. Also closes the no-slip-weight objection to the residual-floor result in closed form, and adds a wall-clock cost measurement. Code: this https URL Subjects: Fluid Dynamics (physics.flu-dyn) ; Computational Physics (physics.comp-ph) Cite as: arXiv:2607.10333 [physics.flu-dyn] (or arXiv:2607.10333v3 [physics.flu-dyn] for this version) https://doi.org/10.48550/arXiv.2607.10333 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Ali Jabbary [ view email ] [v1] Sat, 11 Jul 2026 14:19:51 UTC (283 KB) [v2] Thu, 20 Aug 2026 22:06:06 UTC (298 KB) [v3] Tue, 25 Aug 2026 09:05:46 UTC (303 KB) Full-text links: Access Paper: View PDF HTML (experimental) TeX Source view license Current browse context: physics.flu-dyn < prev | next > new | recent | 2026-07 Change to browse by: physics physics.comp-ph References & Citations SciX Google Scholar Semantic Scholar export BibTeX citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer ( What is the Explorer? ) Connected Papers Toggle Connected Papers ( What is Connected Papers? ) Litmaps Toggle Litmaps ( What is Litmaps? ) scite.ai Toggle scite Smart Citations ( What are Smart Citations? ) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv ( What is alphaXiv? ) Links to Code Toggle CatalyzeX Code Finder for Papers ( What is CatalyzeX? ) DagsHub Toggle DagsHub ( What is DagsHub? ) GotitPub Toggle Gotit.pub ( What is GotitPub? ) Huggingface Toggle Hugging Face ( What is Huggingface? ) ScienceCast Toggle ScienceCast ( What is ScienceCast? ) Demos Demos Replicate Toggle Replicate ( What is Replicate? ) Spaces Toggle Hugging Face Spaces ( What is Spaces? ) Spaces Toggle TXYZ.AI ( What is TXYZ.AI? ) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower ( What are Influence Flowers? ) Core recommender toggle CORE Recommender ( What is CORE? ) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs . Which authors of this paper are endorsers? | Disable MathJax ( What is MathJax? ) We gratefully acknowledge support from our major funders , member institutions , and all contributors. About · Help · Contact · Subscribe · Copyright · Privacy · Accessibility · Operational Status (opens in new tab)

Related documents

• NeuroForge: Self-Auditing Neural CFD Surrogates with Calibrated Physics-Residual Trust#670682
• Physics-Informed Non-Dimensionalisation for Neural Solvers#684012
• Physics-Informed Conformal Prediction: Embedding PDE Consistency into Distribution-Free Uncertainty Quantification for Neural Operators#999920
• A Physics-Augmented Deep Learning Framework for Classifying Single Molecule Force Spectroscopy Data.#469126
• PhysSAE: Mechanistic Interpretability of PINNs with Sparse Autoencoders#1083214