Deep Learning-Driven Inverse Design of Computational Spectrometers
Leyuan Zhang, Yu Chen, Zhihao Li, Tao Xia, An He, Yi Cai, Gangxiang Shen, Gordon Ning Liu
Soochow University
阅读操作
确认中在文库中上传 PDF 后可生成中文音频讲解。
摘要与影响
We propose a computational spectrometer based on deep learning algorithms. The device consists of a beam-splitting network and 32 waveguide filter arrays implemented using four-level parallel cascaded micro-ring resonators with distinct spectral responses. During the design process, the correlation coefficient of the transmission matrix associated with the structural mapping is optimized via deep learning, enabling inverse design of the corresponding device structure. Simulation results demonstrate that the proposed device is capable of reconstructing both sparse and continuous spectra over a wavelength range from 1500 to 1600 nm, with a spectral resolution of approximately 0.4 nm.
逐年被引趋势
暂无年度引用数据
关键指标
同类平均 = 1
同领域 · 同年份 · 同类型
Google Scholar 与 OpenAlex 的被引统计范围不同,数值存在差异属正常。
AI 辅助阅读
依据:摘要
可就本文提问;依据不足时会说明。
学术脉络
学科主题
工程Photonic and Optical Devices
Metamaterials and Metasurfaces Applications · Neural Networks and Reservoir Computing