Predictive and generative machine learning models for photonic crystals

Nanophotonics

article

Thomas Christensen¹  Marin Soljačić¹  Charlotte Loh²  Stjepan Picek³  Domagoj Jakobović⁴  Li Jing¹  Sophie Fisher¹  Vladimir Ceperic¹  John D. Joannopoulos¹ 

[1]Department of Physics, Massachusetts Institute of Technology

[2]Department of Electrical Engineering and Computer Science, Massachusetts Institute of Technology

[3]Faculty of Electrical Engineering, Mathematics and Computer Science, Delft University of Technology

[4]Faculty of Electrical Engineering and Computing, University of Zagreb

关键词: generative models;    inverse design;    machine learning;    neural networks;    photonic crystals;   

DOI  :  10.1515/nanoph-2020-0197

学科分类：社会科学、人文和艺术（综合）

来源: De Gruyter

【 摘 要 】

The prediction and design of photonic features have traditionally been guided by theory-driven computational methods, spanning a wide range of direct solvers and optimization techniques. Motivated by enormous advances in the field of machine learning, there has recently been a growing interest in developing complementary data-driven methods for photonics. Here, we demonstrate several predictive and generative data-driven approaches for the characterization and inverse design of photonic crystals. Concretely, we built a data set of 20,000 two-dimensional photonic crystal unit cells and their associated band structures, enabling the training of supervised learning models. Using these data set, we demonstrate a high-accuracy convolutional neural network for band structure prediction, with orders-of-magnitude speedup compared to conventional theory-driven solvers. Separately, we demonstrate an approach to high-throughput inverse design of photonic crystals via generative adversarial networks, with the design goal of substantial transverse-magnetic band gaps. Our work highlights photonic crystals as a natural application domain and test bed for the development of data-driven tools in photonics and the natural sciences.

【 授权许可】

CC BY