Lynch Sean, LaMountain Jacob, Fan Bo, Bu Jie, Raju Amogh, Wasserman Daniel, Karpatne Anuj, Podolskiy Viktor A
Miner School of Computer Science, University of Massachusetts Lowell, Lowell, Massachusetts 01854, United States.
Department of Physics and Applied Physics, University of Massachusetts Lowell, Lowell, Massachusetts 01854, United States.
ACS Photonics. 2025 Jul 31;12(8):4279-4288. doi: 10.1021/acsphotonics.5c00552. eCollection 2025 Aug 20.
While machine learning (ML) has found multiple applications in photonics, traditional "black box" ML models typically require prohibitively large training data sets. Generation of such data, as well as the training processes themselves, consume significant resources, often limiting practical applications of ML. Here, we demonstrate that embedding Maxwell's equations into ML design and training significantly reduces the required amount of data and improves the physics-consistency and generalizability of ML models, opening the road to practical ML tools that do not need extremely large training sets. The proposed physics-guided machine learning (PGML) approach is illustrated on the example of predicting complex field distributions within hyperbolic meta-material photonic funnels, based on multilayered plasmonic-dielectric composites. The hierarchical network design used in this study enables knowledge transfer and points to the emergence of effective medium theories within neural networks.
虽然机器学习（ML）在光子学领域有多种应用，但传统的“黑箱”ML模型通常需要数量大得令人望而却步的训练数据集。生成这样的数据以及训练过程本身都消耗大量资源，这常常限制了ML的实际应用。在此，我们证明将麦克斯韦方程组嵌入到ML设计和训练中，能显著减少所需的数据量，并提高ML模型的物理一致性和通用性，为无需极大训练集的实用ML工具开辟了道路。所提出的物理引导机器学习（PGML）方法通过基于多层等离子体 - 电介质复合材料预测双曲超材料光子漏斗内的复杂场分布的例子进行了说明。本研究中使用的分层网络设计实现了知识转移，并指出了神经网络中有效介质理论的出现。
