Machine learning analysis of a Fano resonance based plasmonic refractive index sensor using U shaped resonators
Abstract Plasmonic sensors have received special consideration for refractive index (RI) measurement due to the benefits of compact footprints and high sensitivities. To fulfill such conditions, a Fano resonance (FR)-based RI sensor using plasmonic nano-structures is designed and analyzed here. The...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-07-01
|
| Series: | Scientific Reports |
| Online Access: | https://doi.org/10.1038/s41598-025-08508-y |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849238776399790080 |
|---|---|
| author | Shiva Khani Pejman Rezaei Mohammad Rahmanimanesh |
| author_facet | Shiva Khani Pejman Rezaei Mohammad Rahmanimanesh |
| author_sort | Shiva Khani |
| collection | DOAJ |
| description | Abstract Plasmonic sensors have received special consideration for refractive index (RI) measurement due to the benefits of compact footprints and high sensitivities. To fulfill such conditions, a Fano resonance (FR)-based RI sensor using plasmonic nano-structures is designed and analyzed here. The presented topology comprises a metal–insulator–metal waveguide, a U-shaped, and an inverted U-shaped resonator. The transmission spectrum is obtained utilizing the finite-difference time-domain method. Two FRs appear in the transmission spectrum that are suitable options for sensing performance. The best values of two important factors are a sensitivity of 571.4 nm/RIU and a figure of merit of 14,987 RIU−1 for the first FR (598 nm). Furthermore, the transmittance values at intermediate wavelengths with four geometrical parameters and the RI of the analyte are predicted utilizing the Extreme Randomized Tree regression model. This model is evaluated utilizing an adjusted R square score (Adj-R2S) as an assessment parameter using the value of nmin = 3 and a test case of 10%. The Adj-R2S closes 1, showing that transmittance values can be forecasted with high precision. Applying this method decreases the simulation time and resources by 90%. The presented sensor with machine learning behavior prediction ability can be utilized for RI sensing performance. |
| format | Article |
| id | doaj-art-918285dff4ff4fbeb1143242ca0ee0f2 |
| institution | Kabale University |
| issn | 2045-2322 |
| language | English |
| publishDate | 2025-07-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-918285dff4ff4fbeb1143242ca0ee0f22025-08-20T04:01:24ZengNature PortfolioScientific Reports2045-23222025-07-0115111410.1038/s41598-025-08508-yMachine learning analysis of a Fano resonance based plasmonic refractive index sensor using U shaped resonatorsShiva Khani0Pejman Rezaei1Mohammad Rahmanimanesh2Faculty of Electrical and Computer Engineering, Semnan UniversityFaculty of Electrical and Computer Engineering, Semnan UniversityFaculty of Electrical and Computer Engineering, Semnan UniversityAbstract Plasmonic sensors have received special consideration for refractive index (RI) measurement due to the benefits of compact footprints and high sensitivities. To fulfill such conditions, a Fano resonance (FR)-based RI sensor using plasmonic nano-structures is designed and analyzed here. The presented topology comprises a metal–insulator–metal waveguide, a U-shaped, and an inverted U-shaped resonator. The transmission spectrum is obtained utilizing the finite-difference time-domain method. Two FRs appear in the transmission spectrum that are suitable options for sensing performance. The best values of two important factors are a sensitivity of 571.4 nm/RIU and a figure of merit of 14,987 RIU−1 for the first FR (598 nm). Furthermore, the transmittance values at intermediate wavelengths with four geometrical parameters and the RI of the analyte are predicted utilizing the Extreme Randomized Tree regression model. This model is evaluated utilizing an adjusted R square score (Adj-R2S) as an assessment parameter using the value of nmin = 3 and a test case of 10%. The Adj-R2S closes 1, showing that transmittance values can be forecasted with high precision. Applying this method decreases the simulation time and resources by 90%. The presented sensor with machine learning behavior prediction ability can be utilized for RI sensing performance.https://doi.org/10.1038/s41598-025-08508-y |
| spellingShingle | Shiva Khani Pejman Rezaei Mohammad Rahmanimanesh Machine learning analysis of a Fano resonance based plasmonic refractive index sensor using U shaped resonators Scientific Reports |
| title | Machine learning analysis of a Fano resonance based plasmonic refractive index sensor using U shaped resonators |
| title_full | Machine learning analysis of a Fano resonance based plasmonic refractive index sensor using U shaped resonators |
| title_fullStr | Machine learning analysis of a Fano resonance based plasmonic refractive index sensor using U shaped resonators |
| title_full_unstemmed | Machine learning analysis of a Fano resonance based plasmonic refractive index sensor using U shaped resonators |
| title_short | Machine learning analysis of a Fano resonance based plasmonic refractive index sensor using U shaped resonators |
| title_sort | machine learning analysis of a fano resonance based plasmonic refractive index sensor using u shaped resonators |
| url | https://doi.org/10.1038/s41598-025-08508-y |
| work_keys_str_mv | AT shivakhani machinelearninganalysisofafanoresonancebasedplasmonicrefractiveindexsensorusingushapedresonators AT pejmanrezaei machinelearninganalysisofafanoresonancebasedplasmonicrefractiveindexsensorusingushapedresonators AT mohammadrahmanimanesh machinelearninganalysisofafanoresonancebasedplasmonicrefractiveindexsensorusingushapedresonators |