Deep-Learning-Enabled On-Demand Design of Chiral Metamaterials
Проектирование хиральных метаматериалов по требованию с использованием глубокого обучения
2018-06-01
SCID: 54.1/vqrt7ju8
Discuss with AI
bidirectional neural networkschiral metamaterialschiroptical responsedeep-learning-based modelinverse design
Figures from the paper
Abstract (AI)
Deep-learning framework has significantly impelled the development of modern machine learning technology by continuously pushing the limit of traditional recognition and processing of images, speech, and videos. In the meantime, it starts to penetrate other disciplines, such as biology, genetics, materials science, and physics. Here, we report a deep-learning-based model, comprising two bidirectional neural networks assembled by a partial stacking strategy, to automatically design and optimize three-dimensional chiral metamaterials with strong chiroptical responses at predesignated wavelengths. The model can help to discover the intricate, nonintuitive relationship between a metamaterial structure and its optical responses from a number of training examples, which circumvents the time-consuming, case-by-case numerical simulations in conventional metamaterial designs. This approach not only realizes the forward prediction of optical performance much more accurately and efficiently but also enables one to inversely retrieve designs from given requirements. Our results demonstrate that such a data-driven model can be applied as a very powerful tool in studying complicated light-matter interactions and accelerating the on-demand design of nanophotonic devices, systems, and architectures for real world applications.
Key Findings
1
Developed a deep-learning model made of two bidirectional neural networks with a partial stacking strategy to design and optimize 3D chiral metamaterials.
2
Framework enables accurate and efficient forward prediction of optical performance and inverse retrieval of designs for given target wavelengths.
3
Model discovers complex, nonintuitive relationships between metamaterial structure and optical responses from training examples, reducing need for case-by-case numerical simulations.
4
Model produces strong chiroptical responses at predesignated wavelengths, enabling on-demand design and optimization of nanophotonic devices.
Research Object
Three-dimensional chiral metamaterials (nanophotonic chiral structures)
Research Subject
Design and optimization of chiroptical responses (forward prediction and inverse retrieval of optical performance) at predesignated wavelengths using a deep-learning model
Publication Details
Publication Date
2018-06-01
Journal
Publisher
ISSN
Cited by
919
Access Type
Author Information
Download PDF
Subscribe to digest
References available in scid.ai5
ImageNet classification with deep convolutional neural networks2017
Deep Neural Networks for Acoustic Modeling in Speech Recognition: The Shared Views of Four Research Groups2012
Machine learning in materials informatics: recent applications and prospects2017
Negative Refractive Index in Chiral Metamaterials2009
Optical chiral metamaterials: a review of the fundamentals, fabrication methods and applications2016
Cited by6
Tunable nanophotonics enabled by chalcogenide phase‐change materials2020
Artificial Intelligence and Advanced Materials2022
Intelligent nanophotonics: when machine learning sheds light2025
Applied Artificial Intelligence in Materials Science and Material Design2025
Metamaterials: The Art in Materials Science2024
Technology Landscape Review of In-Sensor Photonic Intelligence: From Optical Sensors to Smart Devices2025