MaxwellNet: Physics-driven deep neural network training based on Maxwell's equations
arXiv:2107.06164 · doi:10.1063/5.0071616
Abstract
Maxwell's equations govern light propagation and its interaction with matter. Therefore, the solution of Maxwell's equations using computational electromagnetic simulations plays a critical role in understanding light-matter interaction and designing optical elements. Such simulations are often time-consuming and recent activities have been described to replace or supplement them with trained deep neural networks (DNNs). Such DNNs typically require extensive, computationally demanding simulations using conventional electromagnetic solvers to compose the training dataset. In this paper, we present a novel scheme to train a DNN that solves Maxwell's equations speedily and accurately without relying on other computational electromagnetic solvers. Our approach is to train a DNN using the residual of Maxwell's equations as the physics-driven loss function for a network that finds the electric field given the spatial distribution of the material property. We demonstrate it by training a single network that simultaneously finds multiple solutions of various aspheric micro-lenses. Furthermore, we exploit the speed of this network in a novel inverse design scheme to design a micro-lens that maximizes a desired merit function. We believe that our approach opens up a novel way for light simulation and optical design of photonics devices.
References in corpus (16)
- PyTorch: An Imperative Style, High-Performance Deep Learning Library
- Machine Learning for Fluid Mechanics
- Artificial Neural Networks for Solving Ordinary and Partial Differential Equations
- DGM: A deep learning algorithm for solving partial differential equations
- Outlook for inverse design in nanophotonics
- Training deep neural networks for the inverse design of nanophotonic structures
- Subwavelength-thick Lenses with High Numerical Apertures and Large Efficiency Based on High Contrast Transmitarrays
- Inverse design and demonstration of a compact and broadband on-chip wavelength demultiplexer
- A Generative Model for Inverse Design of Metamaterials
- Physics Informed Deep Learning (Part I): Data-driven Solutions of Nonlinear Partial Differential Equations
- Freeform Diffractive Metagrating Design Based on Generative Adversarial Networks
- High-NA Achromatic Metalenses by Inverse Design
- Deep Learning Models for Global Coordinate Transformations that Linearize PDEs
- Weakly-Supervised Deep Learning of Heat Transport via Physics Informed Loss
- MeshSDF: Differentiable Iso-Surface Extraction
- Deep-learning PDEs with unlabeled data and hardwiring physics laws