research
The Cheap Physics Model Taught the Surrogate What to Correct
Analytical priors cut prediction error for side-branch resonators when only 20 to 70 high-fidelity simulations were available.
Summary
Analytical priors cut prediction error for side-branch resonators when only 20 to 70 high-fidelity simulations were available.
The framework either retains the analytical resonator model as a baseline and learns its discrepancy or distills that mapping into a self-contained prior before calibration. Using 86 simulation-labelled geometries and 8,998 analytical-only examples, residual support-vector regression reduced mean absolute error from 1.333 hertz for the analytical model to 0.426 hertz; a fully fine-tuned prior MLP reached 0.371 hertz. These figures describe one rectangular Helmholtz-resonator study, but they quantify how low-cost physics can improve data efficiency.
Why it matters
Analytical priors cut prediction error for side-branch resonators when only 20 to 70 high-fidelity simulations were available.
Limits and context
- Using 86 simulation-labelled geometries and 8,998 analytical-only examples, residual support-vector regression reduced mean absolute error from 1.333 hertz for the analytical model to 0.426 hertz; a fully fine-tuned prior MLP reached 0.371 hertz.
Key claims
Analytical priors cut prediction error for side-branch resonators when only 20 to 70 high-fidelity simulations were available.
Qualification: Using 86 simulation-labelled geometries and 8,998 analytical-only examples, residual support-vector regression reduced mean absolute error from 1.333 hertz for the analytical model to 0.426 hertz; a fully fine-tuned prior MLP reached 0.371 hertz.
Evidence: source-2026-08-18-007
Sources
- arXiv preprint 2608.16873arXiv · primary research
Corrections
No corrections have been recorded for this story.