Files in this item
Accurate and efficient prediction of photonic crystal waveguide bandstructures using neural networks
Item metadata
dc.contributor.author | Schwahn, Caspar | |
dc.contributor.author | Schulz, Sebastian A. | |
dc.date.accessioned | 2023-07-18T11:30:16Z | |
dc.date.available | 2023-07-18T11:30:16Z | |
dc.date.issued | 2023-06-14 | |
dc.identifier | 286076316 | |
dc.identifier | 10204948-782c-41fa-827b-6892e5bea142 | |
dc.identifier | 85164597568 | |
dc.identifier.citation | Schwahn , C & Schulz , S A 2023 , ' Accurate and efficient prediction of photonic crystal waveguide bandstructures using neural networks ' , OSA Continuum , vol. 2 , no. 6 , 485342 , pp. 1479-1489 . https://doi.org/10.1364/OPTCON.485342 | en |
dc.identifier.issn | 2578-7519 | |
dc.identifier.other | ORCID: /0000-0001-5169-0337/work/139156699 | |
dc.identifier.uri | https://hdl.handle.net/10023/27979 | |
dc.description | Funding: Engineering and Physical Sciences Research Council - EP/V029975/1. | en |
dc.description.abstract | We demonstrate the use of neural networks to predict the optical properties of photonic crystal waveguides (PhCWs) with high accuracy and significantly faster computation times compared to traditional simulation methods. Using 100,000 PhCW designs and their simulated bandstructures, we trained a neural network to achieve a test set relative error of 0.103% in predicting gap guided bands. We use pre-training to improve neural network performance, and numerical differentiation to accurately predict group index curves. Our approach allows for rapid, application-specific tailoring of PhCWs with a runtime of sub-milliseconds per design, a significant improvement over conventional simulation techniques. | |
dc.format.extent | 11 | |
dc.format.extent | 5115820 | |
dc.language.iso | eng | |
dc.relation.ispartof | OSA Continuum | en |
dc.subject | QC Physics | en |
dc.subject | NDAS | en |
dc.subject | MCC | en |
dc.subject.lcc | QC | en |
dc.title | Accurate and efficient prediction of photonic crystal waveguide bandstructures using neural networks | en |
dc.type | Journal article | en |
dc.contributor.sponsor | EPSRC | en |
dc.contributor.institution | University of St Andrews. School of Physics and Astronomy | en |
dc.identifier.doi | https://doi.org/10.1364/OPTCON.485342 | |
dc.description.status | Peer reviewed | en |
dc.identifier.grantnumber | EP/V029975/1 | en |
This item appears in the following Collection(s)
Items in the St Andrews Research Repository are protected by copyright, with all rights reserved, unless otherwise indicated.