Global optimization of dielectric metasurfaces using a physics-driven neural network

By Jiaqi Jiang, Jonathan A. Fan. Nano letters (Print), 2019

398 citations recorded by the source corpus.

We present a global optimizer, based on a conditional generative neural network, which can output ensembles of highly efficient topology-optimized metasurfaces operating across a range of parameters. A key feature of the network is that it initially generates a distribution of devices that broadly samples the design space, and then shifts and refines this distribution towards favorable design space regions over the course of optimization. Training is performed by calculating the forward and adjoint electromagnetic simulations of outputted devices and using the subsequent efficiency gradients for backpropagation. With metagratings operating across a range of wavelengths and angles as a model system, we show that devices produced from the trained generative network have efficiencies comparable to or better than the best devices produced by adjoint-based topology optimization, while requiring less computational cost. Our reframing of adjoint-based optimization to the training of a generative neural network applies generally to physical systems that can utilize gradients to improve performance.

Subfields: Aerospace Engineering, Atomic and Molecular Physics, and Optics, Electronic, Optical and Magnetic Materials

View Paper: https://www.semanticscholar.org/paper/c5c1229bc7126d7afaf73b571effe9211050c1b3

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Aerospace Engineering

1. Yongmin Liu
2. Peter R. Wiecha
3. Yun Raymond Fu
4. C. Girard
5. O. Muskens
6. A. Arbouet

In Atomic and Molecular Physics, and Optics

1. Yongmin Liu
2. Xianzhe Zhang
3. Yun Raymond Fu
4. Yihao Xu
5. Peter R. Wiecha
6. O. Muskens
7. C. Girard
8. A. Arbouet

In Electronic, Optical and Magnetic Materials

1. Yihao Xu
2. Yongmin Liu
3. Peter R. Wiecha
4. C. Girard
5. O. Muskens
6. A. Arbouet

Citations in the corpus

• Deep learning in nano-photonics: inverse design and beyond (2020, methodology): “For the training, gradients of the design efficiency are calculated via adjoint simulations and re-injected for back-propagation through the network [98].”
• Interfacing photonics with artificial intelligence: an innovative design strategy for photonic structures and devices based on artificial neural networks (2021, background): “[100] with permission; (c) is reproduced from Ref.”