Inverse Design of Distributed Bragg Reflectors Using Deep Learning
Distributed Bragg Reflectors are optical structures capable of manipulating light behaviour, which are formed by stacking layers of thin-film materials. The inverse design of such structures is desirable, but not straightforward using conventional numerical methods. This study explores the applicati...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-05-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/12/10/4877 |
| _version_ | 1827670589160030208 |
|---|---|
| author | Sarah Head Mehdi Keshavarz Hedayati |
| author_facet | Sarah Head Mehdi Keshavarz Hedayati |
| author_sort | Sarah Head |
| collection | DOAJ |
| description | Distributed Bragg Reflectors are optical structures capable of manipulating light behaviour, which are formed by stacking layers of thin-film materials. The inverse design of such structures is desirable, but not straightforward using conventional numerical methods. This study explores the application of Deep Learning to the design of a six-layer system, through the implementation of a Tandem Neural Network. The challenge is split into three sections: the generation of training data using the Transfer Matrix method, the design of a Simulation Neural Network (SNN) which maps structural geometry to spectral output, and finally an Inverse Design Neural Network (IDNN) which predicts the geometry required to produce target spectra. The latter enables the designer to develop custom multilayer systems with desired reflection properties. The SNN achieved an average accuracy of 97% across the dataset, with the IDNN achieving 94%. By using this inverse design method, custom-made reflectors can be manufactured in milliseconds, significantly reducing the cost of generating photonic devices and thin-film optics. |
| first_indexed | 2024-03-10T03:25:09Z |
| format | Article |
| id | doaj.art-2edf34c8c20d4541ae876c9b19d5fdf1 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-10T03:25:09Z |
| publishDate | 2022-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-2edf34c8c20d4541ae876c9b19d5fdf12023-11-23T09:54:29ZengMDPI AGApplied Sciences2076-34172022-05-011210487710.3390/app12104877Inverse Design of Distributed Bragg Reflectors Using Deep LearningSarah Head0Mehdi Keshavarz Hedayati1Department of Engineering, Durham University, Durham DH1 3LE, UKDepartment of Engineering, Durham University, Durham DH1 3LE, UKDistributed Bragg Reflectors are optical structures capable of manipulating light behaviour, which are formed by stacking layers of thin-film materials. The inverse design of such structures is desirable, but not straightforward using conventional numerical methods. This study explores the application of Deep Learning to the design of a six-layer system, through the implementation of a Tandem Neural Network. The challenge is split into three sections: the generation of training data using the Transfer Matrix method, the design of a Simulation Neural Network (SNN) which maps structural geometry to spectral output, and finally an Inverse Design Neural Network (IDNN) which predicts the geometry required to produce target spectra. The latter enables the designer to develop custom multilayer systems with desired reflection properties. The SNN achieved an average accuracy of 97% across the dataset, with the IDNN achieving 94%. By using this inverse design method, custom-made reflectors can be manufactured in milliseconds, significantly reducing the cost of generating photonic devices and thin-film optics.https://www.mdpi.com/2076-3417/12/10/4877Machine Learninginverse designtandem networkchromaticityDistributed Bragg Reflector |
| spellingShingle | Sarah Head Mehdi Keshavarz Hedayati Inverse Design of Distributed Bragg Reflectors Using Deep Learning Applied Sciences Machine Learning inverse design tandem network chromaticity Distributed Bragg Reflector |
| title | Inverse Design of Distributed Bragg Reflectors Using Deep Learning |
| title_full | Inverse Design of Distributed Bragg Reflectors Using Deep Learning |
| title_fullStr | Inverse Design of Distributed Bragg Reflectors Using Deep Learning |
| title_full_unstemmed | Inverse Design of Distributed Bragg Reflectors Using Deep Learning |
| title_short | Inverse Design of Distributed Bragg Reflectors Using Deep Learning |
| title_sort | inverse design of distributed bragg reflectors using deep learning |
| topic | Machine Learning inverse design tandem network chromaticity Distributed Bragg Reflector |
| url | https://www.mdpi.com/2076-3417/12/10/4877 |
| work_keys_str_mv | AT sarahhead inversedesignofdistributedbraggreflectorsusingdeeplearning AT mehdikeshavarzhedayati inversedesignofdistributedbraggreflectorsusingdeeplearning |