English

Miniaturized spectrometer enabled by end-to-end deep learning on large-scale radiative cavity array

Optics 2024-11-21 v1

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, we propose and demonstrate a mini-spectrometer that combines a large-scale radiative cavity array with end-to-end deep learning networks. Specifically, we utilize high-Q bound states in continuum cavities with distinct radiation characteristics as the fundamental units to achieve parallel spectral detection. We realize a 36 ×\times 30 cavity array that spans a wide spectral range from 1525 to 1605 nm with quality factors above 10^4. We further train a deep network with 8000 outputs 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.

Keywords

Cite

@article{arxiv.2411.13353,
  title  = {Miniaturized spectrometer enabled by end-to-end deep learning on large-scale radiative cavity array},
  author = {Xinyi Zhou and Cheng Zhang and Xiaoyu Zhang and Yi Zuo and Zixuan Zhang and Feifan Wang and Zihao Chen and Hongbin Li and Chao Peng},
  journal= {arXiv preprint arXiv:2411.13353},
  year   = {2024}
}

Comments

31 pages, 5 figures

R2 v1 2026-06-28T20:06:31.676Z