Optimization of an H0 photonic crystal nanocavity using machine learning

• Abe, Ryotaro

• Takeda, Taichi

• Shiratori, Ryo

• Shirakawa, Shinichi

• Saito, Shota

• Baba, Toshihiko

Abstract

Using machine learning, we optimized an ultrasmall photonic crystal nanocavity to attain a high Q. Training data were collected via finite-difference time-domain simulation for models with randomly shifted holes, and a fully connected neural network (NN) was trained, resulting in a coefficient of determination between predicted and calculated values of 0.977. By repeating NN training and optimization of the Q value on the trained NN, the Q was roughly improved by a factor of 10–20 for various situations. Assuming a 180-nm-thick semiconductor slab at a wavelength approximately 1550 nm, we obtained Q = 1,011,400 in air; 283,200 in a solution, which was suitable for biosensing; and 44,600 with a nanoslot for high sensitivity. Important hole positions were also identified using the linear Lasso regression algorithm.

Journal

• Optics Letters

  Optics Letters 45 (2), 319-322, 2020-01-15

  OSA

Keywords

• Photonic Crystals and Devices
• Cavity quantum electrodynamics
• Laser operation
• Neural networks
• Photonic crystal cavities
• Photonic crystals
• Stochastic gradient descent

Details

• CRID: 1050002213033984000
• NII Article ID: 120006812630
• NII Book ID: AA11868198
• ISSN: 15394794
• ISSN: 01469592
• DOI: 10.1364/ol.381616
• Web Site: http://hdl.handle.net/10131/00013045
• Web Site: https://opg.optica.org/viewmedia.cfm?URI=ol-45-2-319&seq=0
• Text Lang: en
• Article Type: journal article
• Data Source:
  • IRDB
  • Crossref
  • CiNii Articles
  • KAKEN