Shengmei Ou , Jiakang Xu , Jiming Wang , Yulian Zhu , Xiaorong Gu , Tong Wu , Youwen Liu
{"title":"Deep learning-assisted focus engineering for metalens design with high numerical aperture cylindrical vector beams","authors":"Shengmei Ou , Jiakang Xu , Jiming Wang , Yulian Zhu , Xiaorong Gu , Tong Wu , Youwen Liu","doi":"10.1016/j.photonics.2025.101396","DOIUrl":null,"url":null,"abstract":"<div><div>Deep learning, in comparison to traditional optimization algorithms, offers significant advantages in addressing complex problems involving multi-dimensional design parameters for the customization of three-dimensional focal fields. In this paper, we present a design method that combines Richards-Wolf vector diffraction theory and neural network techniques for achieving the customization of different focal fields. We utilize a Physics-Connected Neural Network (PCNN) to devise a discrete filter with 25 rings for guiding the structure of the all-dielectric metalens, thereby facilitating the inverse design of optical needles, optical tubes, and flat-top light fields with an extended focal depth (>10<em>λ</em>). The results demonstrate that when combined with a physical model, the neural network effectively adapts to diverse design objectives, reduces design complexity, and improves the efficiency of the design process.</div></div>","PeriodicalId":49699,"journal":{"name":"Photonics and Nanostructures-Fundamentals and Applications","volume":"65 ","pages":"Article 101396"},"PeriodicalIF":2.9000,"publicationDate":"2025-05-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Photonics and Nanostructures-Fundamentals and Applications","FirstCategoryId":"101","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S156944102500046X","RegionNum":3,"RegionCategory":"物理与天体物理","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"MATERIALS SCIENCE, MULTIDISCIPLINARY","Score":null,"Total":0}
引用次数: 0
Abstract
Deep learning, in comparison to traditional optimization algorithms, offers significant advantages in addressing complex problems involving multi-dimensional design parameters for the customization of three-dimensional focal fields. In this paper, we present a design method that combines Richards-Wolf vector diffraction theory and neural network techniques for achieving the customization of different focal fields. We utilize a Physics-Connected Neural Network (PCNN) to devise a discrete filter with 25 rings for guiding the structure of the all-dielectric metalens, thereby facilitating the inverse design of optical needles, optical tubes, and flat-top light fields with an extended focal depth (>10λ). The results demonstrate that when combined with a physical model, the neural network effectively adapts to diverse design objectives, reduces design complexity, and improves the efficiency of the design process.
期刊介绍:
This journal establishes a dedicated channel for physicists, material scientists, chemists, engineers and computer scientists who are interested in photonics and nanostructures, and especially in research related to photonic crystals, photonic band gaps and metamaterials. The Journal sheds light on the latest developments in this growing field of science that will see the emergence of faster telecommunications and ultimately computers that use light instead of electrons to connect components.