Free-Form Diffractive Metagrating Design Based on Generative Adversarial Networks
Free-Form Diffractive Metagrating Design Based on Generative Adversarial Networks
复制标题
DOI：
10.1021/acsnano.9b02371
复制
发表时间：
2019-08-01
期刊：
影响因子：
17.1
通讯作者：
Fan, Jonathan A.
中科院分区：
文献类型：
--
作者：
Jiang, Jiaqi;Sell, David;Fan, Jonathan A.
超表面设计的一个关键挑战是开发能够有效且高效地生产高性能设备的算法。基于迭代优化的设计方法可以突破超表面的性能极限，但它们需要大量的计算资源，这限制了它们在少量微型设备上的实现。我们证明，生成神经网络可以根据周期性的、拓扑优化的元光栅图像进行训练，以产生在广泛的偏转角和波长范围内运行的高效、拓扑复杂的设备。这些设计的进一步迭代优化可以产生具有增强鲁棒性和效率的设备，并且这些设备可以用作网络细化的额外训练数据。通过这种方式，生成网络可以通过一次性计算成本进行训练，并用作一种设计工具，以促进近乎最优、拓扑复杂的设备设计的产生。我们设想这种数据驱动的设计方法可以应用于其他需要设计在广泛的参数空间中运行的功能元素的物理科学领域。
A key challenge in metasurface design is the development of algorithms that can effectively and efficiently produce high-performance devices. Design methods based on iterative optimization can push the performance limits of metasurfaces, but they require extensive computational resources that limit their implementation to small numbers of microscale devices. We show that generative neural networks can train from images of periodic, topology optimized metagratings to produce high-efficiency, topologically complex devices operating over a broad range of deflection angles and wavelengths. Further iterative optimization of these designs yields devices with enhanced robustness and efficiencies, and these devices can be utilized as additional training data for network refinement. In this manner, generative networks can be trained, with a one-time computation cost, and used as a design tool to facilitate the production of near-optimal, topologically complex device designs. We envision that such data-driven design methodologies can apply to other physical sciences domains that require the design of functional elements operating across a wide parameter space.