Open AccessDeep learning for design metamaterial electromagnetic induction transparent device
Author(s) -
Ziming Wei,
Zeyulin Zhang,
Wei Huang,
Shengyan Yin,
Wentao Zhang
Publication year - 2021
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1775/1/012005
Subject(s) - metamaterial , computer science , terahertz radiation , tunable metamaterials , transmission (telecommunications) , electronic engineering , topology (electrical circuits) , physics , optics , electrical engineering , engineering , telecommunications
In this paper, we propose a deep learning model that can be used to reverse design metamaterial electromagnetic induction transparent (EIT) devices. This is a problem that is difficult to achieve with traditional numerical calculation methods. We use the coordinates of six specific points on the EIT transmission spectrum as the input of the neural network, and then the network can predict the structural parameters of the corresponding EIT device. We cite an example to prove that our method can be used to efficiently reverse design the structure of EIT devices. We believe that this method will open up a new way for the structural design of EIT devices and has great potential for expanding the application of terahertz EIT metamaterials.