Abstract

Designing thermal radiation metamaterials is challenging especially for problems with high degrees of freedom and complex objectives. In this Letter, we develop a hybrid materials informatics approach which combines the adversarial autoencoder and Bayesian optimization to design narrowband thermal emitters at different target wavelengths. With only several hundreds of training data sets, new structures with optimal properties can be quickly determined in a compressed two-dimensional latent space. This enables the optimal design by calculating far less than 0.001% of the total candidate structures, which greatly decreases the design period and cost. The proposed design framework can be easily extended to other thermal radiation metamaterials design with higher dimensional features.

© 2022 Optica Publishing Group

Design of a highly selective radiative cooling structure accelerated by materials informatics

Jiang Guo, Shenghong Ju, and Junichiro Shiomi
Opt. Lett. 45(2) 343-346 (2020)

High-throughput screening of a high-Q mid-infrared Tamm emitter by material informatics

Wang Xi, Yida Liu, Jinlin Song, Run Hu, and Xiaobing Luo
Opt. Lett. 46(4) 888-891 (2021)

Fano resonance in a dolomite phase-change multilayer design for dynamically tunable omnidirectional monochromatic thermal emission

Zahra Rahimian Omam, Amir Ghobadi, Bahram Khalichi, and Ekmel Ozbay
Opt. Lett. 47(22) 5781-5784 (2022)

High-performance narrowband thermal emitter based on aperiodic Tamm plasmon structures assisted by inverse design

Qianli Qiu, Dongjie Zhou, Jinguo Zhang, Chong Tan, Qianqian Xu, Zongkun Zhang, Zhengji Wen, Yan Sun, Ning Dai, and Jiaming Hao
Opt. Lett. 48(22) 6000-6003 (2023)

Combined multi-band infrared camouflage and thermal management via a simple multilayer structure design

Lei Wang, Yue Yang, Xianglin Tang, Bin Li, Yizhi Hu, Yonggang Zhu, and Huizhu Yang
Opt. Lett. 46(20) 5224-5227 (2021)