{"title":"A physics-aware neural network for effective refractive index prediction of photonic waveguides","authors":"Hasan Said Ünal, Ahmet Cemal Durgun","doi":"10.1007/s11082-024-08009-8","DOIUrl":null,"url":null,"abstract":"<div><p>Neural network (NN)—based surrogates have been effectively used for modeling dynamic systems, including photonic devices. However, black-box data-driven modeling approaches significantly suffer from performance reduction in high-dimensional spaces.As a remedy, we propose a novel physics-aware NN architecture for the effective index prediction of photonic strip waveguides. The model learns a translation between the strip waveguide and an equivalent infinite slab waveguide by employing physical loss terms in the loss function. The proposed method exhibits significantly lower error, with more than <span>\\(50\\%\\)</span> reduction, compared to a black-box NN and a variational method. Because of its physical basis, the proposed NN can predict field distributions in rectangular waveguides and the effective indices of higher-order modes.</p></div>","PeriodicalId":720,"journal":{"name":"Optical and Quantum Electronics","volume":"57 1","pages":""},"PeriodicalIF":3.3000,"publicationDate":"2025-01-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s11082-024-08009-8.pdf","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Optical and Quantum Electronics","FirstCategoryId":"5","ListUrlMain":"https://link.springer.com/article/10.1007/s11082-024-08009-8","RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"ENGINEERING, ELECTRICAL & ELECTRONIC","Score":null,"Total":0}
引用次数: 0
Abstract
Neural network (NN)—based surrogates have been effectively used for modeling dynamic systems, including photonic devices. However, black-box data-driven modeling approaches significantly suffer from performance reduction in high-dimensional spaces.As a remedy, we propose a novel physics-aware NN architecture for the effective index prediction of photonic strip waveguides. The model learns a translation between the strip waveguide and an equivalent infinite slab waveguide by employing physical loss terms in the loss function. The proposed method exhibits significantly lower error, with more than \(50\%\) reduction, compared to a black-box NN and a variational method. Because of its physical basis, the proposed NN can predict field distributions in rectangular waveguides and the effective indices of higher-order modes.
期刊介绍：
Optical and Quantum Electronics provides an international forum for the publication of original research papers, tutorial reviews and letters in such fields as optical physics, optical engineering and optoelectronics. Special issues are published on topics of current interest.
Optical and Quantum Electronics is published monthly. It is concerned with the technology and physics of optical systems, components and devices, i.e., with topics such as: optical fibres; semiconductor lasers and LEDs; light detection and imaging devices; nanophotonics; photonic integration and optoelectronic integrated circuits; silicon photonics; displays; optical communications from devices to systems; materials for photonics (e.g. semiconductors, glasses, graphene); the physics and simulation of optical devices and systems; nanotechnologies in photonics (including engineered nano-structures such as photonic crystals, sub-wavelength photonic structures, metamaterials, and plasmonics); advanced quantum and optoelectronic applications (e.g. quantum computing, memory and communications, quantum sensing and quantum dots); photonic sensors and bio-sensors; Terahertz phenomena; non-linear optics and ultrafast phenomena; green photonics.
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号
