Optimization of photonic crystal nanocavities based on deep learning

Abstract

An approach to optimizing the Q factors of two-dimensional photonic crystal (2D-PC) nanocavities based on deep learning is proposed and demonstrated. We prepare a dataset consisting of 1000 nanocavities generated by randomly displacing the positions of many air holes of a base nanocavity and their Q factors calculated by a first-principle method. We train a four-layer neural network including a convolutional layer to recognize the relationship between the air holes' displacements and the Q factors using the prepared dataset. After the training, the neural network becomes able to estimate the Q factors from the air holes' displacements with an error of 13% in standard deviation. Crucially, the trained neural network can estimate the gradient of the Q factor with respect to the air holes' displacements very quickly based on back-propagation. A nanocavity structure with an extremely high Q factor of 1.58 x 10^9 is successfully obtained by optimizing the positions of 50 air holes over ~10^6 iterations, having taken advantage of the very fast evaluation of the gradient in high-dimensional parameter space. The obtained Q factor is more than one order of magnitude higher than that of the base cavity and more than twice that of the highest Q factors reported so far for cavities with similar modal volumes. This approach can optimize 2D-PC structures over a parameter space of a size unfeasibly large for previous optimization methods based solely on direct calculations. We believe this approach is also useful for improving other optical characteristics.

14 pages, 8 figures

References in corpus (4)

• Training deep neural networks for the inverse design of nanophotonic structures
• Laser oscillation in a strongly coupled single quantum dot-nanocavity system
• General Recipe for Designing Photonic Crystal Cavities
• A single-photon switch and transistor enabled by a solid-state quantum memory

Cited by in corpus (28)

• Deep neural networks for the evaluation and design of photonic devices
• Uncertainty Quantification in Machine Learning for Engineering Design and Health Prognostics: A Tutorial
• Minireview on Disordered Optical Metasurfaces
• Enhanced Light-Matter Interactions in Dielectric Nanostructures via Machine Learning Approach
• Deep Learning Reveals Underlying Physics of Light-matter Interactions in Nanophotonic Devices
• General Inverse Design of Thin-Film Metamaterials With Convolutional Neural Networks
• Iterative optimization of photonic crystal nanocavity designs by using deep neural networks
• A topological encoding method for data-driven photonics inverse design
• Plug-and-play quantum devices with efficient fiber-quantum dot interface
• Machine learning and evolutionary algorithm studies of graphene metamaterials for optimized plasmon-induced transparency
• Drawing Phase Diagrams of Random Quantum Systems by Deep Learning the Wave Functions
• Surface-passivated high-Q GaAs photonic crystal nanocavity with quantum dots
• Fast Design of Plasmonic Metasurfaces Enabled by Deep Learning
• Fundamental thermal noise limits for optical microcavities
• AI Algorithm for Mode Classification of PCF SPR Sensor Design
• Deep learning-based design of broadband GHz complex and random metasurfaces
• Rapid Exploration of Topological Band Structures using Deep Learning
• Data driven approaches in nanophotonics: A review of AI-enabled metadevices
• Deep Neural Network Inverse Design of Integrated Nanophotonic Devices
• Strong coupling between a single quantum dot and an L4/3 photonic crystal nanocavity
• Predicting VCSEL Emission Properties Using Transformer Neural Networks
• Automated Discovery of Coupled Mode Setups
• Improved design and experimental demonstration of ultrahigh-Q C${}_{\text{6}}$-symmetric H1 hexapole photonic crystal nanocavities
• LLM4Laser: Large Language Models Automate the Design of Lasers
• High-Freedom Inverse Design with Deep Neural Network for Metasurface Filter in the Visible
• Generative Deep Learning Model for a Multi-level Nano-Optic Broadband Power Splitter
• Data-Efficient Electromagnetic Surrogate Solver Through Dissipative Relaxation Transfer Learning
• A Reinforcement learning method for Optical Thin-Film Design