Scholarlink

<p>Neural network (NN)—based surrogates have been effectively used for modeling dynamic systems, including photonic devices. However, black-box data-driven modeling approaches significantly suffer from performance reduction in high-dimensional spaces.As a remedy, we propose a novel physics-aware NN architecture for the effective index prediction of photonic strip waveguides. The model learns a translation between the strip waveguide and an equivalent infinite slab waveguide by employing physical loss terms in the loss function. The proposed method exhibits significantly lower error, with more than <InlineEquation ID="IEq1"> <InlineMediaObject> <ImageObject Color="BlackWhite" FileRef="11082_2024_8009_Article_IEq1.gif" Format="GIF" Height="16" Rendition="HTML" Resolution="72" Type="Linedraw" Width="31" /> </InlineMediaObject> <EquationSource Format="TEX">\(50\%\)</EquationSource> <EquationSource Format="MATHML"><math> <mrow> <mn>50</mn> <mo>%</mo> </mrow> </math></EquationSource> </InlineEquation> reduction, compared to a black-box NN and a variational method. Because of its physical basis, the proposed NN can predict field distributions in rectangular waveguides and the effective indices of higher-order modes.</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

A physics-aware neural network for effective refractive index prediction of photonic waveguides

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年1月11日

查看全文
  • Hasan Said Ünal,
  • Ahmet Cemal Durgun

摘要

Neural network (NN)—based surrogates have been effectively used for modeling dynamic systems, including photonic devices. However, black-box data-driven modeling approaches significantly suffer from performance reduction in high-dimensional spaces.As a remedy, we propose a novel physics-aware NN architecture for the effective index prediction of photonic strip waveguides. The model learns a translation between the strip waveguide and an equivalent infinite slab waveguide by employing physical loss terms in the loss function. The proposed method exhibits significantly lower error, with more than \(50\%\) 50 % reduction, compared to a black-box NN and a variational method. Because of its physical basis, the proposed NN can predict field distributions in rectangular waveguides and the effective indices of higher-order modes.