Deep learning modeling approach for metasurfaces with high degrees of freedom
Deep learning modeling approach for metasurfaces with high degrees of freedom
复制标题
DOI：
10.1364/oe.401960
复制
发表时间：
2020-10-12
期刊：
影响因子：
3.8
通讯作者：
Zhang, Hualiang
中科院分区：
文献类型：
--
作者：
An, Sensong;Zheng, Bowen;Zhang, Hualiang
超表面在成形光学波前方面显示出有前途的潜力，同时与庞大的几何光学器件相比保持紧凑。超表面的基本构建块--超原子的设计通常依赖于试错法来实现目标电磁响应。该过程包括表征具有不同物理和几何参数的大量元原子设计，这需要巨大的计算资源。本文介绍了一种基于深度学习的元表面/元原子建模方法，可以在保持准确性的同时显著缩短表征时间。基于卷积神经网络（CNN）结构，所提出的深度学习网络能够以几乎自由的2D模式和不同的晶格尺寸、材料折射率和厚度对元原子进行建模。此外，所提出的方法具有预测元原子的宽光谱响应在毫秒的时间尺度，有吸引力的应用程序需要快速按需设计和优化的元原子/元表面的能力。(C)2020年美国光学学会根据OSA开放获取出版协议的条款
Metasurfaces have shown promising potentials in shaping optical wavefronts while remaining compact compared to bulky geometric optics devices. The design of meta-atoms, the fundamental building blocks of metasurfaces, typically relies on trial and error to achieve target electromagnetic responses. This process includes the characterization of an enormous amount of meta-atom designs with varying physical and geometric parameters, which demands huge computational resources. In this paper, a deep learning-based metasurface/meta-atom modeling approach is introduced to significantly reduce the characterization time while maintaining accuracy. Based on a convolutional neural network (CNN) structure, the proposed deep learning network is able to model meta-atoms with nearly freeform 2D patterns and different lattice sizes, material refractive indices and thicknesses. Moreover, the presented approach features the capability of predicting a meta-atom's wide spectrum response in the timescale of milliseconds, attractive for applications necessitating fast on-demand design and optimization of a metaatom/metasurface. (C) 2020 Optical Society of America under the terms of the OSA Open Access Publishing Agreement