Nanophotonic particle simulation and inverse design using artificial neural networks

By John Peurifoy, Yichen Shen, Li Jing, Yi Yang, Fidel Cano-Renteria, B. DeLacy, John D. Joannopoulos, Max Tegmark, Marin Soljačić. Science Advances, 2017

892 citations recorded by the source corpus.

New deep learning techniques may hold the key to solving intractable photonics problems. We propose a method to use artificial neural networks to approximate light scattering by multilayer nanoparticles. We find that the network needs to be trained on only a small sampling of the data to approximate the simulation to high precision. Once the neural network is trained, it can simulate such optical processes orders of magnitude faster than conventional simulations. Furthermore, the trained neural network can be used to solve nanophotonic inverse design problems by using back propagation, where the gradient is analytical, not numerical.

Subfields: Artificial Intelligence, Atomic and Molecular Physics, and Optics, Electrical and Electronic Engineering

View Paper: https://www.semanticscholar.org/paper/12e02594e51ae17d7fe5ad6df532d13f50b86b03

How researchers see this paper

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

In Artificial Intelligence

In Atomic and Molecular Physics, and Optics

In Electrical and Electronic Engineering

Citations in the corpus

Intelligent nanophotonics: merging photonics and artificial intelligence at the nanoscale (2018, methodology): “ical methods provides a suitable playground for efficient data generation. Figures 11(A) and 11(B) exemplify this by considering the scattering problem of a SiO 2 /TiO 2 multilayer spherical particle [151]. With analytical solutions derived from the transfer matrix method, 50000 samples were generat”
Deep Neural Network Inverse Design of Integrated Photonic Power Splitters (2019, methodology): “It has received some attention in optical community and there has been several recent work on reverse modeling for design of nano-structured optical components using DNN [19-25], as well as hardware implementation of an artificial neural network [26-30].”
Deep learning in nano-photonics: inverse design and beyond (2020, background): “Other examples are the design of chiral plasmonic structures [71,85], dielectric structures [86], multi-shell nano-spheres [56,87], invisibility cloaks [88 – 90], or metasurface design [91 – 93].”
Probabilistic Representation and Inverse Design of Metamaterials Based on a Deep Generative Model with Semi‐Supervised Learning Strategy (2019, background): “More recent works sought to deal with the inverse design by DL under various scenarios, like plasmonic waveguide [48], optical power splitter [49], plasmonic metamaterials [50], chiral metamaterials [51] and nanophotonic particles [52].”
Interpretable inverse design of particle spectral emissivity using machine learning (2020, methodology): “…machine learning has also shown some success in further accelerating the inverse design process by performing the inverse mapping in a single-shot (i.e. without iteratively solving the forward problem) for some optics problems (e.g., concentric spherical shells 12 and periodic metasurfaces 13–16 ).”
Deep physical neural networks trained with backpropagation (2021, background): “Ultimately, PNNs provide routes to improving the energy efficiency and speed of machine learning by many orders of magnitude, and pathways to automatically designing complex functional devices, such as functional nanoparticles 28 , robots 25,26 and smart sensors 30–32 .”