A general machine learning-based approach for inverse design of one-dimensional photonic crystals toward targeted visible light reflection spectrum
A general machine learning-based approach for inverse design of one-dimensional photonic crystals toward targeted visible light reflection spectrum
复制标题
DOI：
10.1016/j.optcom.2022.127920
复制
发表时间：
2021-09
影响因子：
2.4
通讯作者：
Tao Zhan;Quan-Shan Liu;Lu Qiu;Yuan Sun;T. Wen;Rui Zhang
中科院分区：
文献类型：
--
作者：
Tao Zhan;Quan-Shan Liu;Lu Qiu;Yuan Sun;T. Wen;Rui Zhang
数据驱动方法作为一种廉价而有效的反求设计方法，越来越多地应用于光学系统的开发。光学性质（例如，光子晶体（PC）的带隙特性与它们的光反射光谱特性密切相关。因此，寻找最佳的PC结构（在一个预先指定的参数空间内），产生最接近目标光谱的反射光谱是一个有趣的和有意义的逆设计问题，虽然相关的研究仍然有限。在这里，我们报告了一个普遍有效的基于机器学习的一维光子晶体（1DPC）的逆设计方法，专注于具有高度实用性的可见光光谱。对于给定的一类1DPC系统，统一结构中的深度神经网络（DNN）首先在来自相当大的前向计算（从层厚度到光谱）的数据上进行训练。然后，基于DNN向后预测（从光谱到层厚度）、向前计算和Monte Carlo移动的相干集成，开发了迭代优化方案。我们采用这种新的方法，四个有代表性的类1DPC系统，包括周期性结构与两个，三个，四层重复单元和异质结构。该方法成功地收敛到各种目标光谱的最佳1DPC结构的解决方案，而不管它们的精确可重构性。文中给出了几个具体的设计实例，包括对特殊结构的“矩形”、窄带隙红光、绿色、蓝光反射光谱以及在整个可见光区具有高反射率的宽带隙反射光谱的逆向设计。值得注意的是，结果表明，该方法可以有效地找出最佳层厚度，即使它们远远超出DNN原始训练数据覆盖的范围。
Data-driven methods have increasingly been applied to the development of optical systems as inexpensive and effective inverse design approaches. Optical properties (e.g., band-gap properties) of photonic crystals (PCs) are closely associated with characteristics of their light reflection spectra. Finding optimal PC constructions (within a pre-specified parameter space) that generate reflection spectra closest to a targeted spectrum is thus an interesting and meaningful inverse design problem, although relevant studies are still limited. Here we report a generally effective machine learning-based inverse design approach for one-dimensional photonic crystals (1DPCs), focusing on visible light spectra which are of high practical relevance. For a given class of 1DPC system, a deep neural network (DNN) in a unified structure is first trained over data from sizeable forward calculations (from layer thicknesses to spectrum). An iterative optimization scheme is then developed based on a coherent integration of DNN backward predictions (from spectrum to layer thicknesses), forward calculations, and Monte Carlo moves. We employ this new approach to four representative classes of 1DPC systems including periodic structures with two-, three-, and four-layer repeating units and a heterostructure. The approach successfully converges to solutions of optimal 1DPC constructions for various targeted spectra regardless of their exact achievability. Several demonstrating examples are presented and discussed in detail, including the inverse designs toward specially constructed “rectangle-shaped”, narrow-bandgap red-, green-, or blue-light reflection spectrum and wide-bandgap reflection spectrum that has high reflectivity in the whole visible light region. Remarkably, the results show that the approach can efficiently find out optimal layer thicknesses even when they are far outside the range covered by the original training data of DNN.