A mixture-density-based tandem optimization network for on-demand inverse design of thin-film high reflectors.

A mixture-density-based tandem optimization network for on-demand inverse design of thin-film high reflectors.
复制标题

DOI:
10.1515/nanoph-2021-0392
复制
发表时间:
2021-11
期刊:
影响因子:
7.5
通讯作者:
--
中科院分区:
物理与天体物理1区
文献类型:
--
作者:

文献摘要

参考文献

相似文献

深度学习(DL)已成为光子逆向设计的一种有前景的工具。然而,尽管在以近乎瞬时的读出方式检索适度复杂的光谱方面取得了初步成功,但与先进的优化技术相比,深度学习辅助设计方法在准确性方面往往表现不佳,并且在处理实际有用的光谱方面尚未证明具有竞争力。在这里,我们介绍了一种串联优化模型,该模型结合了混合密度网络(MDN)和全连接(FC)网络来​​逆向设计实用的薄膜高反射器。 MDN 的多模态性质允许访问由概率分布描述的无限候选设计,这些设计由 FC 网络迭代采样和评估,以实现快速优化。我们证明所提出的模型可以检索 20 层薄膜结构的反射光谱。更有趣的是,它高精度地再现了源自物理原理的高反射器的周期性结构,尽管训练数据中不包含此类信息。还展示了具有扩展高反射率区域的改进设计。我们的方法将深度学习的高效率优势与优化后的性能改进相结合,为实际应用提供高效且按需的逆向设计。
Deep learning (DL) has emerged as a promising tool for photonic inverse design. Nevertheless, despite the initial success in retrieving spectra of modest complexity with nearly instantaneous readout, DL-assisted design methods often underperform in accuracy compared with advanced optimization techniques and have not proven competitive in handling spectra of practical usefulness. Here, we introduce a tandem optimization model that combines a mixture density network (MDN) and a fully connected (FC) network to inversely design practical thin-film high reflectors. The multimodal nature of the MDN gives access to infinite candidate designs described by probability distributions, which are iteratively sampled and evaluated by the FC network to allow for rapid optimization. We show that the proposed model can retrieve the reflectance spectra of 20-layer thin-film structures. More interestingly, it reproduces with high precision the periodic structures of high reflectors derived from physical principles, even though no such information is included in the training data. Improved designs with extended high-reflectance zones are also demonstrated. Our approach combines the high-efficiency advantage of DL with the optimization-enabled performance improvement, enabling efficient and on-demand inverse design for practical applications.
DOI: 10.1103/physrevlett.124.010508
发表时间: 2020-01-08
影响因子: 8.6
作者:
Iten, Raban;Metger, Tony;del Rio, Lidia
通讯作者: del Rio, Lidia
DOI: 10.1515/nanoph-2020-0407
发表时间: 2021-01-01
期刊: NANOPHOTONICS
影响因子: 7.5
作者:
Jiang, Jiaqi;Fan, Jonathan A.
通讯作者: Fan, Jonathan A.
DOI: 10.3390/ma9060497
发表时间: 2016-06-21
期刊: Materials (Basel, Switzerland)
影响因子: --
作者:
Keshavarz Hedayati M;Elbahri M
通讯作者: Elbahri M
DOI: 10.1021/acsnano.9b02371
发表时间: 2019-08-01
期刊: ACS NANO
影响因子: 17.1
作者:
Jiang, Jiaqi;Sell, David;Fan, Jonathan A.
通讯作者: Fan, Jonathan A.
DOI: 10.1364/osac.420977
发表时间: 2021-03-15
期刊: OSA CONTINUUM
影响因子: 1.6
作者:
Hegde, Ravi
通讯作者: Hegde, Ravi