Work

Modeling Microwave S-parameters using Frequency-scaled Rational Gaussian Process Kernels

Year: 2024

Type: conference-paper

Abstract: This work presents a machine learning technique to model the complex-valued scattering parameters (S-parameters) of passive microwave devices as a function of frequency and a set of design variables. The proposed Gaussian process (GP) model intricately models the real and imaginary parts of the S-parameters by employing a physics-informed kernel, adept at representing complex holomorphic functions and incorporating the Hermitian symmetry inherent in scattering parameters. Additionally, to extend the kernel's capabilities to higher dimensions beyond standard GP techniques, it is extended with a frequency scaling, enhancing the modeling capacity. The resulting physics-informed frequency-scaled GP model accurately predicts the S-parameter values at desired parameter configurations in the design space. One application example demonstrates the superiority of the new kernel, compared to standard GP kernels.

Source: IEEE Conference on Electrical Performance of Electronic Packaging and Systems (EPEPS)

DOI: 10.1109/epeps61853.2024.10754263

Authors: Thijs Ullrick, Dirk Deschrijver, Wim Bogaerts, Tom Dhaene

Institutions: Ghent University, IMEC

Language: English

Topic: Microwave Engineering and Waveguides

Subfield: Electrical and Electronic Engineering

Field: Engineering

Domain: Physical Sciences

Open Access status: green

Funder: Fonds Wetenschappelijk Onderzoek

Award: MALEPHICENT: MAchine Learning to Engineer Photonic Integrated Circuits for ENhanced Tolerance