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

• DOI: 10.48550/arxiv.2411.13353
• Publication Date: 2024-01-01
• Authors: Zhou, Xinyi; Zhang, Cheng; Zhang, Xiaoyu; Zuo, Yi; Zhang, Zixuan; Wang, Feifan; Chen, Zihao; Li, Hongbin; Peng, Chao
• Keywords: FOS: Physical sciences; Physics - Optics; Optics (physics.optics)

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.<br/>31 pages, 5 figures<br/>