Scholarlink

<p>An accurate waveguide width extraction methodology is demonstrated by developing a deep-learning neural network (DNN) framework synergized with a single low-order Mach-Zehnder interferometer (MZI). Utilizing its intrinsic capacity for complex nonlinear capture, the proposed DNN achieves a simulation-to-prediction accuracy of 0.15&#xa0;nm on a test dataset, establishing a robust geometry mapping. By leveraging fabrication tolerance analysis and group-index estimation from C-band MZI interference spectra, our method directly extracts the as-fabricated waveguide width via a pre-trained DNN. Experimental validation on 30 devices demonstrates an experimental estimation accuracy of 3.28&#xa0;nm when compared to SEM measurements. Additionally, the system operates with a single low-order MZI featuring a reduced arm-length difference of 26.672&#xa0;μm, while the conventional ones exceeding 100&#xa0;μm. The superior precision and miniaturization capability make our approach an effective strategy for fabrication monitoring and high-density photonic circuit characterization.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

DNN-assisted waveguide width extraction via optical measurement of a single low-order Mach-Zehnder interferometer

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年3月5日

查看全文
  • Fuling Wang,
  • Hao You,
  • Xiao Xu,
  • Liuge Du,
  • Chonglei Sun,
  • Jia Zhao

摘要

An accurate waveguide width extraction methodology is demonstrated by developing a deep-learning neural network (DNN) framework synergized with a single low-order Mach-Zehnder interferometer (MZI). Utilizing its intrinsic capacity for complex nonlinear capture, the proposed DNN achieves a simulation-to-prediction accuracy of 0.15 nm on a test dataset, establishing a robust geometry mapping. By leveraging fabrication tolerance analysis and group-index estimation from C-band MZI interference spectra, our method directly extracts the as-fabricated waveguide width via a pre-trained DNN. Experimental validation on 30 devices demonstrates an experimental estimation accuracy of 3.28 nm when compared to SEM measurements. Additionally, the system operates with a single low-order MZI featuring a reduced arm-length difference of 26.672 μm, while the conventional ones exceeding 100 μm. The superior precision and miniaturization capability make our approach an effective strategy for fabrication monitoring and high-density photonic circuit characterization.