Physics-guided hierarchical neural networks for Maxwell's equations in plasmonic metamaterials
arXiv:2502.17644 · doi:10.1021/acsphotonics.5c00552
Abstract
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 metamaterial 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.
References in corpus (9)
- DeepONet: Learning nonlinear operators for identifying differential equations based on the universal approximation theorem of operators
- Hyperbolic metamaterials: fundamentals and applications
- Learning data driven discretizations for partial differential equations
- Deep neural networks for the evaluation and design of photonic devices
- Global optimization of dielectric metasurfaces using a physics-driven neural network
- Cavity-excited Huygens' metasurface antennas: near-unity aperture efficiency from arbitrarily-large apertures
- Meta-material photonic funnels for sub-diffraction light compression and propagation
- Self-supervised learning of hologram reconstruction using physics consistency
- Active learning of deep surrogates for PDEs: Application to metasurface design