Abstract
Composed of a large number of subwavelength unit cells with designable geometries, metamaterials have been widely studied to achieve extraordinary advantageous and unusual optical properties. However, ordinary computer simulator requires a time-consuming fine-tuning to find a proper design of metamaterial for a specific optical property, making the design stage a critical bottleneck in large scale applications of metamaterials. This paper investigates the metamaterial design under the framework of computer experiments, with emphasis on dealing with the challenge of designing numerous unit cells with functional responses, simultaneously, which is not common in traditional computer experiments. We formulate the multiple related design targets as a multitarget design problem. Leveraging on the similarity between different designs, we propose an efficient Bayesian optimization strategy with a parsimonious surrogate model and an integrated acquisition function to design multiple unit cells with very few function evaluations. A wide range of simulations confirm the effectiveness and superiority of the proposed approach compared to the naive strategies where the multiple unit cells are dealt with separately or sequentially. Such a rapid design strategy has the potential to greatly promote large scale applications of metamaterials in practice.
Funding Statement
This work was supported by the National Natural Science Foundation of China (grant numbers 11931001 and 11771242), the Beijing Academy of Artificial Intelligence (grant number BAAI2019ZD0103), the State Key Laboratory of Meta-RF Electromagnetic Modulation Technology and Guangdong Provincial Key Laboratory of Meta-RF Microwave.
Acknowledgements
Ke Deng and Chunlin Ji are co-corresponding authors of this paper. We thank Mr. Yunshui Zhang of Department of Mathematical Sciences, Tsinghua University and Dr. Xiao Guo of Shenzhen Kuang-Chi Institute of Advanced Technology for insightful discussions in early stage of this study.
Citation
Yang Yang. Chunlin Ji. Ke Deng. "Rapid design of metamaterials via multitarget Bayesian optimization." Ann. Appl. Stat. 15 (2) 768 - 796, June 2021. https://doi.org/10.1214/20-AOAS1426
Information