{"title":"Miniaturized Spectrometer Enabled by End-to-End Deep Learning on Large-Scale Radiative Cavity Array","authors":"Xinyi Zhou, Cheng Zhang, Xiaoyu Zhang, Yi Zuo, Zixuan Zhang, Feifan Wang, Zihao Chen, Hongbin Li, Chao Peng","doi":"10.1002/adom.202501196","DOIUrl":null,"url":null,"abstract":"<p>Miniaturized (mini-) spectrometers are highly desirable tools for chemical, biological, and medical diagnostics because of their potential for portable and in situ spectral detection. In this work, a mini-spectrometer that combines a large-scale radiative cavity array with end-to-end deep learning networks is proposed and demonstrated. Specifically, high-<i>Q</i> bound states are utilized in continuum cavities with distinct radiation characteristics as the fundamental units to achieve parallel spectral detection. An array of resonators with quality factors above 10<sup>4</sup> over a wide spectral range, from 1525 to 1605 nm, is realized. A deep network with 8000 outputs is further trained to directly map arbitrary spectra to array responses excited by the out-of-plane incident. Experimental results demonstrate that the proposed mini-spectrometer can resolve unknown spectra with a resolution of 0.048 nm in a bandwidth of 80 nm and fidelity exceeding 95%, thus offering a promising method for compact, high resolution, and broadband spectroscopy.</p>","PeriodicalId":116,"journal":{"name":"Advanced Optical Materials","volume":"13 26","pages":""},"PeriodicalIF":7.2000,"publicationDate":"2025-08-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Advanced Optical Materials","FirstCategoryId":"88","ListUrlMain":"https://advanced.onlinelibrary.wiley.com/doi/10.1002/adom.202501196","RegionNum":2,"RegionCategory":"材料科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"MATERIALS SCIENCE, MULTIDISCIPLINARY","Score":null,"Total":0}
引用次数: 0
Abstract
Miniaturized (mini-) spectrometers are highly desirable tools for chemical, biological, and medical diagnostics because of their potential for portable and in situ spectral detection. In this work, a mini-spectrometer that combines a large-scale radiative cavity array with end-to-end deep learning networks is proposed and demonstrated. Specifically, high-Q bound states are utilized in continuum cavities with distinct radiation characteristics as the fundamental units to achieve parallel spectral detection. An array of resonators with quality factors above 104 over a wide spectral range, from 1525 to 1605 nm, is realized. A deep network with 8000 outputs is further trained to directly map arbitrary spectra to array responses excited by the out-of-plane incident. Experimental results demonstrate that the proposed mini-spectrometer can resolve unknown spectra with a resolution of 0.048 nm in a bandwidth of 80 nm and fidelity exceeding 95%, thus offering a promising method for compact, high resolution, and broadband spectroscopy.
期刊介绍:
Advanced Optical Materials, part of the esteemed Advanced portfolio, is a unique materials science journal concentrating on all facets of light-matter interactions. For over a decade, it has been the preferred optical materials journal for significant discoveries in photonics, plasmonics, metamaterials, and more. The Advanced portfolio from Wiley is a collection of globally respected, high-impact journals that disseminate the best science from established and emerging researchers, aiding them in fulfilling their mission and amplifying the reach of their scientific discoveries.