Mask Reconstruction via Kernel-Based Surrogate Modeling for Automated Circulator Design

Abstract

This letter introduces a mask-based surrogate modeling framework which generalizes the feature-based paradigm for efficient microwave design exploration using a limited number of full-wave simulations. Unlike feature-based approaches, which extract scalar performance metrics, the proposed method reconstructs the complete S-parameter boundary contour within the operating band. This preserves each design's parametric signature and enables on-demand evaluation of multiple performance specifications without model retraining. The framework employs two Vector-Valued Kernel Ridge Regression models to predict boundary coordinates from geometric parameters. Validation on a three-port circulator demonstrates accurate reconstruction and rapid exploration of thousands of candidate designs.

Surrogate Modeling and Explainable Artificial Intelligence for Complex Systems: A Workflow for Automated Simulation Exploration
Paul Saves, Pramudita Satria Palar, Muhammad Robani +7
HAL31 Oct 2026PreprintCC BY 4.0Full textGeneral mathematics Statistical & nonlinear physicsHAL
A hierarchy of physics-embedded neural operators for structural dynamic surrogate modelingA hierarchy of physics-embedded neural operators for structural dynamic surrogate modeling
Amir Ansrollahi, Mehmet Sefa Orak
arXiv4 Nov 2026PreprintarXiv licenceFull textMathematical physics Computational physicsarXiv
A Review of Bayesian Surrogate Modeling for High-Dimensional Computer Simulations
Gavin Collins, Gabriel Huerta, J. Derek Tucker +1
arXiv22 Oct 2026PreprintarXiv licenceFull textStatisticsarXiv
Accelerating droplet-laden Stokes flow simulations with hierarchical surrogate modeling
Davide Pradovera, Thomas Frachon, Sara Zahedi
arXiv6 Oct 2026PreprintCC BY 4.0Full textNumerical analysis & scientific computing Fluid dynamicsarXiv
On Kernel Eigen-alignments of KRR: Reconstruction and Generalization
Yang Liu, Ernest Fokoue, Richard Lange +1
arXiv19 Sep 2026PreprintCC BY-SA 4.0Full textStatisticsarXiv

Cite

BibTeX RIS

BibTeX

@article{atlante2026mask,
  title = {{Mask Reconstruction via Kernel-Based Surrogate Modeling for Automated Circulator Design}},
  author = {Marco Atlante and Riccardo Trinchero and Igor Stievano and Mihai Telescu and Vincent Laur and Noël Tanguy},
  journal = {IEEE Microwave and Wireless Technology Letters},
  year = {2026},
  month = sep,
  doi = {10.1109/lmwt.2026.3666201},
  url = {https://univ-brest.hal.science/hal-05734154v1},
  note = {CC BY-NC-ND 4.0},
}

RIS

TY  - JOUR
TI  - Mask Reconstruction via Kernel-Based Surrogate Modeling for Automated Circulator Design
AU  - Marco Atlante
AU  - Riccardo Trinchero
AU  - Igor Stievano
AU  - Mihai Telescu
AU  - Vincent Laur
AU  - Noël Tanguy
PY  - 2026
DA  - 2026/09/01
JO  - IEEE Microwave and Wireless Technology Letters
DO  - 10.1109/lmwt.2026.3666201
UR  - https://univ-brest.hal.science/hal-05734154v1
AB  - This letter introduces a mask-based surrogate modeling framework which generalizes the feature-based paradigm for efficient microwave design exploration using a limited number of full-wave simulations. Unlike feature-based approaches, which extract scalar performance metrics, the proposed method reconstructs the complete S-parameter boundary contour within the operating band. This preserves each design's parametric signature and enables on-demand evaluation of multiple performance specifications without model retraining. The framework employs two Vector-Valued Kernel Ridge Regression models to predict boundary coordinates from geometric parameters. Validation on a three-port circulator demonstrates accurate reconstruction and rapid exploration of thousands of candidate designs.
SN  - 2771-957X
SN  - 2771-9588
ER  -

Abstract

Related

Cite