PreprintarXiv licencearXiv
Physics-constrained neural networks for surrogate modeling of lossless periodic structures
Abstract
We introduce a physics-constrained neural network for the rapid prediction of rigorous coupled-wave analysis outputs in the form of Jones matrices. Starting from energy conservation in lossless layered periodic structures, we use the fact that the scattering outputs lie on a Stiefel manifold. This energy constraint is enforced as a hard condition by projecting onto the manifold using differentiable symmetric orthogonalization. The resulting surrogate enforces energy conservation by construction while preserving differentiability for gradient-based inverse design. The performance and generality of the proposed approach are demonstrated through the inverse design of a diffractive waveguide combiner for augmented reality glasses.
Related
- Mechanism-informed dynamic surrogate modeling for rapid thermal-aberration prediction in bonded optical systems
- Physics-Constrained Neural Surrogate for Domain Growth Prediction in Systems with Conserved Kinetics
- Physics-constrained graph closures and working-point conditioning for a fast surrogate of linac beam dynamics
- Machine learning surrogate modeling with quantile adjustment for landing gear surface pressure fluctuation prediction
- A hierarchy of physics-embedded neural operators for structural dynamic surrogate modelingA hierarchy of physics-embedded neural operators for structural dynamic surrogate modeling
BibTeX
@misc{prehn2026physicsconstrained,
title = {{Physics-constrained neural networks for surrogate modeling of lossless periodic structures}},
author = {Eric Prehn and Peter Jung},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2606.28119},
eprint = {2606.28119},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2606.28119},
}
RIS
TY - UNPB
TI - Physics-constrained neural networks for surrogate modeling of lossless periodic structures
AU - Eric Prehn
AU - Peter Jung
PY - 2026
DA - 2026/09/10
PB - arXiv
DO - 10.48550/arxiv.2606.28119
UR - https://arxiv.org/abs/2606.28119
AB - We introduce a physics-constrained neural network for the rapid prediction of rigorous coupled-wave analysis outputs in the form of Jones matrices. Starting from energy conservation in lossless layered periodic structures, we use the fact that the scattering outputs lie on a Stiefel manifold. This energy constraint is enforced as a hard condition by projecting onto the manifold using differentiable symmetric orthogonalization. The resulting surrogate enforces energy conservation by construction while preserving differentiability for gradient-based inverse design. The performance and generality of the proposed approach are demonstrated through the inverse design of a diffractive waveguide combiner for augmented reality glasses.
ER -