We are interested in exploring the limit in using deep learning (DL) to study the electromagnetic (EM) response for complex and random metasurfaces, without any specific applications in mind. For simplicity, we focus on a simple pure reflection problem of a broadband EM plane wave incident normally on such complex metasurfaces in the frequency regime of 2–12 GHz. In doing so, we create a DL-based framework called the metasurface design deep convolutional neural network (MSDCNN) for both forward and inverse designs of three different classes of complex metasurfaces: (a) arbitrary connecting polygons, (b) basic pattern combination, and (c) fully random binary patterns. The performance of each metasurface is evaluated and cross-benchmarked. Dependent on the type of complex metasurfaces, sample size, and DL algorithms used, the MSDCNN is able to provide good agreement and can be a faster design tool for complex metasurfaces than the traditional full-wave EM simulation methods. However, no single universal deep convolutional neural network model can work well for all metasurface classes based on detailed statistical analysis (such as mean, variance, kurtosis, and mean-squared error). Our findings report important information on the advantages and limitations of current DL models in designing these ultimately complex metasurfaces.

中文翻译：

---

基于深度学习的宽带 GHz 复杂和随机超表面设计

我们有兴趣探索使用深度学习 (DL) 研究复杂和随机超表面的电磁 (EM) 响应的局限性，而不考虑任何特定应用。为简单起见，我们关注一个简​​单的纯反射问题，即宽带 EM 平面波通常入射在 2-12 GHz 频率范围内的这种复杂超表面上。为此，我们创建了一个基于 DL 的框架，称为超曲面设计深度卷积神经网络 (MSDCNN)，用于三种不同类别的复杂超曲面的正向和逆向设计：(a) 任意连接多边形，(b) 基本模式组合， (c) 完全随机的二进制模式。评估和交叉基准测试每个超表面的性能。取决于复杂超表面的类型、样本大小和使用的 DL 算法，MSDCNN 能够提供良好的一致性，并且可以成为比传统全波 EM 模拟方法更快的复杂超表面设计工具。然而，基于详细的统计分析（如均值、方差、峰态和均方误差），没有一个单一的通用深度卷积神经网络模型可以很好地适用于所有超表面类。我们的研究结果报告了有关当前 DL 模型在设计这些最终复杂的超表面方面的优势和局限性的重要信息。