Physics-informed recurrent neural network for time dynamics in optical resonances
Physics-informed recurrent neural network for time dynamics in optical resonances
复制标题
DOI：
10.1038/s43588-022-00215-2
复制
发表时间：
2022-03
期刊：
影响因子：
--
通讯作者：
Yingheng Tang;Jichao Fan;Xinwei Li;Jianzhu Ma;M. Qi;Cunxi Yu;Weilu Gao
中科院分区：
文献类型：
--
作者：
Yingheng Tang;Jichao Fan;Xinwei Li;Jianzhu Ma;M. Qi;Cunxi Yu;Weilu Gao
共振结构和特征在光学科学中是普遍存在的。然而，由于收敛速度慢和时间窗口有限，在现实世界的场景中捕获它们的时间动态遭受长的数据采集时间和低分析精度。在这里，我们报告了一个基于物理信息的递归神经网络，用于预测光共振的时域响应，并通过获取序列的一部分作为输入来推断相应的共振频率。该模型在两步多保真度框架中进行训练，以实现高精度预测，首先使用大量低保真度物理模型生成的合成数据，然后使用一小部分高保真应用特定数据。通过模拟和实验，我们证明了该模型适用于广泛的共振，包括介电超颖表面，石墨烯等离子体和超强耦合朗道极化激元，其中我们的模型捕获小信号特征并学习物理量。所展示的机器学习算法可以帮助加速探索共振增强光物质相互作用下的物理现象和设备设计。
Resonance structures and features are ubiquitous in optical science. However, capturing their time dynamics in real-world scenarios suffers from long data acquisition time and low analysis accuracy due to slow convergence and limited time windows. Here we report a physics-informed recurrent neural network to forecast the time-domain response of optical resonances and infer corresponding resonance frequencies by acquiring a fraction of the sequence as input. The model is trained in a two-step multi-fidelity framework for high-accuracy forecast, using first a large amount of low-fidelity physical-model-generated synthetic data and then a small set of high-fidelity application-specific data. Through simulations and experiments, we demonstrate that the model is applicable to a wide range of resonances, including dielectric metasurfaces, graphene plasmonics and ultra-strongly coupled Landau polaritons, where our model captures small signal features and learns physical quantities. The demonstrated machine-learning algorithm can help to accelerate the exploration of physical phenomena and device design under resonance-enhanced light–matter interaction.