Parametric optimization of the slot waveguide characteristics using a machine-learning approach

Abstract Slot waveguides provide high electric field amplitude and optical power in low-index materials that are not possible with conventional waveguides. This specific property of the slot waveguide provides interaction between active material and electric field, which led to many interesting appl...

Full description

Saved in:
Bibliographic Details
Main Authors: Yadvendra Singh, Suraj Jena, Harish Subbaraman
Format: Article
Language:English
Published: Nature Portfolio 2025-07-01
Series:Scientific Reports
Online Access:https://doi.org/10.1038/s41598-025-07521-5
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849769346566455296
author Yadvendra Singh
Suraj Jena
Harish Subbaraman
author_facet Yadvendra Singh
Suraj Jena
Harish Subbaraman
author_sort Yadvendra Singh
collection DOAJ
description Abstract Slot waveguides provide high electric field amplitude and optical power in low-index materials that are not possible with conventional waveguides. This specific property of the slot waveguide provides interaction between active material and electric field, which led to many interesting applications, such as optical amplification, optical switching, and optical detection in integrated photonics. In the present work, we combine machine learning (ML) algorithms and finite element simulation to predict the power confinement ( $$\hbox {P}_{conf}$$ ) and mode effective index ( $$\hbox {n}_{eff}$$ ) of slot waveguides with respect to geometric parameters such as gap, slab width, and slab height. Three different ML techniques, such as artificial neural network (ANN), support vector regression (SVR), and random forest (RF), were tested to compute performance parameters for the slot waveguide. The RF method outperformed the other two with mean absolute error (MAE), root mean square error (RMSE), coefficient of determination ( $$\hbox {R}^{2}$$ ), and Nash–Sutcliffe efficiency (NSE) values corresponding $$\hbox {n}_{eff}$$ and $$\hbox {P}_{conf}$$ as 0.007, 0.054, 0.961, and 0.960, and 0.129, 0.185, 0.998, and 0.998, respectively. Thus, providing a useful ML methodology for efficient optimization of slot waveguide structures for future applications.
format Article
id doaj-art-e410a72c441c48f08047771ef412438e
institution DOAJ
issn 2045-2322
language English
publishDate 2025-07-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-e410a72c441c48f08047771ef412438e2025-08-20T03:03:27ZengNature PortfolioScientific Reports2045-23222025-07-0115111310.1038/s41598-025-07521-5Parametric optimization of the slot waveguide characteristics using a machine-learning approachYadvendra Singh0Suraj Jena1Harish Subbaraman2School of Electrical Engineering and Computer Science, Oregon State UniversityCollege of Agricultural Science, Oregon State UniversitySchool of Electrical Engineering and Computer Science, Oregon State UniversityAbstract Slot waveguides provide high electric field amplitude and optical power in low-index materials that are not possible with conventional waveguides. This specific property of the slot waveguide provides interaction between active material and electric field, which led to many interesting applications, such as optical amplification, optical switching, and optical detection in integrated photonics. In the present work, we combine machine learning (ML) algorithms and finite element simulation to predict the power confinement ( $$\hbox {P}_{conf}$$ ) and mode effective index ( $$\hbox {n}_{eff}$$ ) of slot waveguides with respect to geometric parameters such as gap, slab width, and slab height. Three different ML techniques, such as artificial neural network (ANN), support vector regression (SVR), and random forest (RF), were tested to compute performance parameters for the slot waveguide. The RF method outperformed the other two with mean absolute error (MAE), root mean square error (RMSE), coefficient of determination ( $$\hbox {R}^{2}$$ ), and Nash–Sutcliffe efficiency (NSE) values corresponding $$\hbox {n}_{eff}$$ and $$\hbox {P}_{conf}$$ as 0.007, 0.054, 0.961, and 0.960, and 0.129, 0.185, 0.998, and 0.998, respectively. Thus, providing a useful ML methodology for efficient optimization of slot waveguide structures for future applications.https://doi.org/10.1038/s41598-025-07521-5
spellingShingle Yadvendra Singh
Suraj Jena
Harish Subbaraman
Parametric optimization of the slot waveguide characteristics using a machine-learning approach
Scientific Reports
title Parametric optimization of the slot waveguide characteristics using a machine-learning approach
title_full Parametric optimization of the slot waveguide characteristics using a machine-learning approach
title_fullStr Parametric optimization of the slot waveguide characteristics using a machine-learning approach
title_full_unstemmed Parametric optimization of the slot waveguide characteristics using a machine-learning approach
title_short Parametric optimization of the slot waveguide characteristics using a machine-learning approach
title_sort parametric optimization of the slot waveguide characteristics using a machine learning approach
url https://doi.org/10.1038/s41598-025-07521-5
work_keys_str_mv AT yadvendrasingh parametricoptimizationoftheslotwaveguidecharacteristicsusingamachinelearningapproach
AT surajjena parametricoptimizationoftheslotwaveguidecharacteristicsusingamachinelearningapproach
AT harishsubbaraman parametricoptimizationoftheslotwaveguidecharacteristicsusingamachinelearningapproach