Do Better Scores Mean Better Physics? Physics-Grounded Explanations for Sim2Real Neural Operators

Title:Do Better Scores Mean Better Physics? Physics-Grounded Explanations for Sim2Real Neural Operators

Abstract:Machine-learning surrogates accelerate physical simulation, but lower prediction error need not coincide with lower error in physically relevant flow statistics. We examine this question for flow around a NACA4418 airfoil using paired computational-fluid-dynamics simulations and experimental particle-image-velocimetry measurements. A mean-preserving input intervention removes velocity fluctuations from selected regions of observed flow histories. Across four neural operators, removing fluctuations from the most energetic 10% of valid observed cells changes forecasts more than equal-area random removal. Because the masks are not matched for removed fluctuation energy, this contrast measures sensitivity, not independent evidence of physical importance. Separately, a CNO has lower velocity-field error but substantially higher two-component fluctuation-energy error than the reference on both analysis subsets. An output attenuation stress test also demonstrates disagreement between benchmark errors and domain-summed fluctuation energy. These single-benchmark results motivate reporting complementary physical diagnostics alongside aggregate prediction scores; they do not establish counterfactual physical correctness.

10 pages, 6 figures. Accepted at the NeurIPS 2026 XAI4Science Workshop, Tiny Paper Track

Machine Learning (cs.LG); Fluid Dynamics (physics.flu-dyn)

arXiv:2610.00415 [cs.LG]

(or arXiv:2610.00415v1 [cs.LG] for this version)

https://doi.org/10.48550/arXiv.2610.00415 Focus to learn more arXiv-issued DOI via DataCite (pending registration)

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.