Wavelength Controllable Forward Prediction and Inverse Design of Nanophotonic Devices Using Deep Learning

2020/10/29 by Yuchen Song, Song, Yuchen, Danshi Wang +7
Engineering · Mathematics · Physics and Astronomy · #Computer science #Demultiplexer #Domain (mathematical analysis) #Electronic engineering #Engineering #Inverse #Materials science #Mathematics #Multiplexing #Nanophotonics #Optics #Optoelectronics #Photonic Crystals and Applications #Photonic and Optical Devices #Physics #Plasmonic and Surface Plasmon Research #Splitter #Telecommunications #Wavelength #Wavelength-division multiplexing #physics.optics

paper · pdf · doi:10.48550/arxiv.2010.15547

published in arXiv (Cornell University) (Cornell University) · Accepted by ECOC2020

openalex publication_date 2020/10/29 · arxiv created 2020/11/06 · arxiv updated 2020/11/09 · openalex created_date 2020/11/09 · openalex updated_date 2026/08/05

Abstract

A deep learning-based wavelength controllable forward prediction and inverse design model of nanophotonic devices is proposed. Both the target time-domain and wavelength-domain information can be utilized simultaneously, which enables multiple functions, including power splitter and wavelength demultiplexer, to be implemented efficiently and flexibly.

Related

• Deep Neural Network Inverse Design of Integrated Nanophotonic Devices
• Improving Fabrication Fidelity of Integrated Nanophotonic Devices Using Deep Learning
• Deep Learning for Design and Retrieval of Nano-photonic Structures
• Artificial Intelligence in Nanophotonics: From Design to Optical Computing
• Hybrid Supervised and Reinforcement Learning for the Design and Optimization of Nanophotonic Structures