Surrogate modeling of passive microwave circuits using recurrent neural networks and domain confinement

Abstract Electromagnetic (EM) simulation is widespread in microwave engineering. EM tools ensure evaluation reliability but incur significant expenses. These can be mitigated by employing surrogate modeling methods, especially to expedite design workflows like local/global optimization or uncertaint...

Full description

Saved in:
Bibliographic Details
Main Authors: Kaustab C. Sahu, Slawomir Koziel, Anna Pietrenko-Dabrowska
Format: Article
Language:English
Published: Nature Portfolio 2025-04-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-025-91643-3
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849700125765533696
author Kaustab C. Sahu
Slawomir Koziel
Anna Pietrenko-Dabrowska
author_facet Kaustab C. Sahu
Slawomir Koziel
Anna Pietrenko-Dabrowska
author_sort Kaustab C. Sahu
collection DOAJ
description Abstract Electromagnetic (EM) simulation is widespread in microwave engineering. EM tools ensure evaluation reliability but incur significant expenses. These can be mitigated by employing surrogate modeling methods, especially to expedite design workflows like local/global optimization or uncertainty quantification. However, building accurate surrogates is a daunting task beyond simple cases (low dimensionality, narrow geometry parameter and frequency ranges). This research suggests a new technique for dependable modeling of microwave circuits. Its main ingredient is a recurrent neural network (RNN) with the main architectural components being bidirectional Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU) layers. These are incorporated to accurately represent frequency relationship within circuit characteristics as well as dependencies between its dimensions and outputs considered as vector-valued functions parameterized by frequency. The network’s hyperparameters are adjusted through Bayesian Optimization (BO). Utilization of frequency as a sequential variable handled by RNN is a distinguishing feature of our approach, which leads to the enhancement of dependability and cost efficiency. Another critical factor is dimension- and volume-wise reduction of the model’s domain achieved through global sensitivity analysis. It allows for additional and dramatic accuracy improvements without diminishing the surrogate’s coverage regarding circuit’s operating parameters. Our methodology has been extensively validated using several microstrip structures. The results demonstrate its competitive performance over a range of kernel-based regression techniques and diverse neural networks. The proposed procedure ensures building models of outstanding predictive power while using small training datasets, which is beyond the capabilities of benchmark algorithms.
format Article
id doaj-art-5c5f4dcfd17f41d1bc5b5b733821e402
institution DOAJ
issn 2045-2322
language English
publishDate 2025-04-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-5c5f4dcfd17f41d1bc5b5b733821e4022025-08-20T03:18:23ZengNature PortfolioScientific Reports2045-23222025-04-0115112010.1038/s41598-025-91643-3Surrogate modeling of passive microwave circuits using recurrent neural networks and domain confinementKaustab C. Sahu0Slawomir Koziel1Anna Pietrenko-Dabrowska2Engineering Optimization & Modeling Center, Reykjavik UniversityEngineering Optimization & Modeling Center, Reykjavik UniversityFaculty of Electronics, Telecommunications and Informatics, Gdansk University of TechnologyAbstract Electromagnetic (EM) simulation is widespread in microwave engineering. EM tools ensure evaluation reliability but incur significant expenses. These can be mitigated by employing surrogate modeling methods, especially to expedite design workflows like local/global optimization or uncertainty quantification. However, building accurate surrogates is a daunting task beyond simple cases (low dimensionality, narrow geometry parameter and frequency ranges). This research suggests a new technique for dependable modeling of microwave circuits. Its main ingredient is a recurrent neural network (RNN) with the main architectural components being bidirectional Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU) layers. These are incorporated to accurately represent frequency relationship within circuit characteristics as well as dependencies between its dimensions and outputs considered as vector-valued functions parameterized by frequency. The network’s hyperparameters are adjusted through Bayesian Optimization (BO). Utilization of frequency as a sequential variable handled by RNN is a distinguishing feature of our approach, which leads to the enhancement of dependability and cost efficiency. Another critical factor is dimension- and volume-wise reduction of the model’s domain achieved through global sensitivity analysis. It allows for additional and dramatic accuracy improvements without diminishing the surrogate’s coverage regarding circuit’s operating parameters. Our methodology has been extensively validated using several microstrip structures. The results demonstrate its competitive performance over a range of kernel-based regression techniques and diverse neural networks. The proposed procedure ensures building models of outstanding predictive power while using small training datasets, which is beyond the capabilities of benchmark algorithms.https://doi.org/10.1038/s41598-025-91643-3Microwave circuitsData-driven surrogatesRecurrent neural networksSensitivity analysisDomain confinement
spellingShingle Kaustab C. Sahu
Slawomir Koziel
Anna Pietrenko-Dabrowska
Surrogate modeling of passive microwave circuits using recurrent neural networks and domain confinement
Scientific Reports
Microwave circuits
Data-driven surrogates
Recurrent neural networks
Sensitivity analysis
Domain confinement
title Surrogate modeling of passive microwave circuits using recurrent neural networks and domain confinement
title_full Surrogate modeling of passive microwave circuits using recurrent neural networks and domain confinement
title_fullStr Surrogate modeling of passive microwave circuits using recurrent neural networks and domain confinement
title_full_unstemmed Surrogate modeling of passive microwave circuits using recurrent neural networks and domain confinement
title_short Surrogate modeling of passive microwave circuits using recurrent neural networks and domain confinement
title_sort surrogate modeling of passive microwave circuits using recurrent neural networks and domain confinement
topic Microwave circuits
Data-driven surrogates
Recurrent neural networks
Sensitivity analysis
Domain confinement
url https://doi.org/10.1038/s41598-025-91643-3
work_keys_str_mv AT kaustabcsahu surrogatemodelingofpassivemicrowavecircuitsusingrecurrentneuralnetworksanddomainconfinement
AT slawomirkoziel surrogatemodelingofpassivemicrowavecircuitsusingrecurrentneuralnetworksanddomainconfinement
AT annapietrenkodabrowska surrogatemodelingofpassivemicrowavecircuitsusingrecurrentneuralnetworksanddomainconfinement