Meta‐Attention Deep Learning for Smart Development of Metasurface Sensors

作者：Yuan Gao, Wei Chen, Fajun Li, Mingyong Zhuang, Yiming Yan, Jun Wang, Xiang Wang, Zhaogang Dong, Wei Ma, Jinfeng Zhu · 发表于：Advanced Science · 年份：2024 · DOI：10.1002/advs.202405750 · 被引用次数：46 · 研究领域：Metamaterials and Metasurfaces Applications、Animal Vocal Communication and Behavior、Plasmonic and Surface Plasmon Research

Optical metasurfaces with pronounced spectral characteristics are promising for sensor applications. Currently, deep learning (DL) offers a rapid manner to design various metasurfaces. However, conventional DL models are usually assumed as black boxes, which is difficult to explain how a DL model learns physical features, and they usually predict optical responses of metasurfaces in a fuzzy way. This makes them incapable of capturing critical spectral features precisely, such as high quality (Q) resonances, and hinders their use in designing metasurface sensors. Here, a transformer-based explainable DL model named Metaformer for the high-intelligence design, which adopts a spectrum-splitting scheme to elevate 99% prediction accuracy through reducing 99% training parameters, is established. Based on the Metaformer, all-dielectric metasurfaces based on quasi-bound states in the continuum (Q-BIC) for high-performance metasensing are designed, and fabrication experiments are guided potently. The explainable learning relies on spectral position encoding and multi-head attention of meta-optics features, which overwhelms traditional black-box models dramatically. The meta-attention mechanism provides deep physics insights on metasurface sensors, and will inspire more powerful DL design applications on other optical devices.