Designing thermal radiation metamaterials via hybrid adversarial autoencoder and Bayesian optimization

Abstract

Designing thermal radiation metamaterials is challenging especially for problems with high degrees of freedom and complex objective. In this letter, we have developed 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 figured out in a compressed 2-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.

References in corpus (7)

• Generative Adversarial Networks: An Overview
• Training deep neural networks for the inverse design of nanophotonic structures
• An Empirical Survey of Data Augmentation for Time Series Classification with Neural Networks
• Machine-Learning-Assisted Metasurface Design for High-Efficiency Thermal Emitter Optimization
• Expanding the horizon of automated metamaterials discovery via quantum annealing
• Materials Informatics for Heat Transfer: Recent Progresses and Perspectives
• Deep learning for the modeling and inverse design of radiative heat transfer

Cited by in corpus (2)

• Enhancing thermoelectric properties of isotope graphene nanoribbons via machine learning guided manipulation of disordered antidots and interfaces
• Data-driven design of multilayer hyperbolic metamaterials for near-field thermal radiative modulator with high modulation contrast