Optimization of metamaterials and metamaterial-microcavity based on deep neural networks. Issue 23 (7th November 2022)

• Record Type: Journal Article
• Authors: Lan, Guoqiang; Wang, Yu; Ou, Jun-Yu
• Is Part Of: Nanoscale advances. Volume 4:Issue 23(2022)
• Page Start: 5137
• Page End: 5143
• Publication Date: 2022-11-07
• Subjects: 620.5
• DOI: 10.1039/d2na00592a
• Languages: English
• ISSNs: 2516-0230

Abstract

Abstract : We use a deep-learning method to optimize the design of split-ring metamaterials and metamaterial-microcavities. We use this method to quickly realize the design of the metamaterial-microcavity with the absorptance peak at 1310 nm. Abstract : Computational inverse-design and forward prediction approaches provide promising pathways for on-demand nanophotonics. Here, we use a deep-learning method to optimize the design of split-ring metamaterials and metamaterial-microcavities. Once the deep neural network is trained, it can predict the optical response of the split-ring metamaterial in a second which is much faster than conventional simulation methods. The pretrained neural network can also be used for the inverse design of split-ring metamaterials and metamaterial-microcavities. We use this method for the design of the metamaterial-microcavity with the absorptance peak at 1310 nm. Experimental results verified that the deep-learning method is a fast, robust, and accurate method for designing metamaterials with complex nanostructures.