2018/05/25 by Zhaocheng Liu, Dayu Zhu, Sean P. Rodrigues +3 · 969 citations
Biochemistry, Genetics and Molecular Biology · Computer Science · Engineering · Materials Science · Mathematics · Physics and Astronomy · #Acoustics #Advanced Optical Imaging Technologies #Animal Vocal Communication and Behavior #Artificial intelligence #Computer science #Fidelity #Generative Design #Generative grammar #Generative model #Geometry #High fidelity #Holography #Intuition #Inverse #Inverse problem #Materials science #Mathematical analysis #Mathematics #Metamaterial #Metamaterials and Metasurfaces Applications #Optics #Physics #Telecommunications #cs.LG #physics.comp-ph #physics.optics
paper · pdf · doi:10.1021/acs.nanolett.8b03171
published in Nano Letters 18(10), 6570-6576 (American Chemical Society) · 15 pages, 4 figures
arxiv created 2018/05/25 · openalex publication_date 2018/09/12 · arxiv updated 2018/11/14 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/05
The advent of metasurfaces in recent years has ushered in a revolutionary means to manipulate the behavior of light on the nanoscale. The design of such structures, to date, has relied on the expertise of an optical scientist to guide a progression of electromagnetic simulations that iteratively solve Maxwell's equations until a locally optimized solution can be attained. In this work, we identify a solution to circumvent this conventional design procedure by means of a deep learning architecture. When fed an input set of customer-defined optical spectra, the constructed generative network generates candidate patterns that match the on-demand spectra with high fidelity. This approach reveals an opportunity to expedite the discovery and design of metasurfaces for tailored optical responses in a systematic, inverse-design manner.