Publisher DOI: 10.1016/j.photonics.2022.101076
Title: Machine learning models for photonic crystals band diagram prediction and gap optimisation
Language: English
Authors: Nikulin, A. 
Zisman, I. 
Eich, Manfred 
Petrov, Alexander Yu.  
Itin, Alexander 
Keywords: Machine learning; Neural networks; Photonic bandgap materials; Photonic crystals
Issue Date: Dec-2022
Source: Photonics and Nanostructures - Fundamentals and Applications 52: 101076 (2022-12)
Abstract (english): 
Data-driven methods of machine learning (ML) have attracted a lot of interest in various fields of physics. Inverse design and optimisation of structured optical metamaterials such as photonic crystals, metasurfaces, and other nanostructured components seem to benefit a lot from this approach in the nearest future. Here we develop several approaches to use ML methods to predict and optimise properties of photonic crystals (e.g. size of bandgaps) effectively. We use a dataset of 2D photonic crystals produced recently in [T.Christinsen et al., Nanophotonics 9, 4183 (2020)]. For improving performance of predictive models, we apply symmetry-aware augmentations and hybrid ML-solver approaches. As a result, considerable improvement in prediction accuracy could be achieved as compared to baseline models. For generative models, we apply variational autoencoders (VAEs) combined with predictor architecture, inspired by related works in chemical design realm. By using latent space optimisation, we achieve good results in the task of increasing bandgaps of photonic structures. The approach seems to be very promising and can be extended to 3D geometries.
ISSN: 1569-4410
Journal: Photonics and nanostructures 
Institute: Optische und Elektronische Materialien E-12 
Document Type: Article
Project: SFB 986: Teilprojekt C01 - Multiskalige photonische Materialien mit anpassbarer Absorption und thermischer Emission 
AI for photonics 
SFB 986: Teilprojekt C02 - Multiskalige photonische Materialien mit anpassbarer radialer Anisotropie 
Peer Reviewed: Yes
Appears in Collections:Publications without fulltext

Show full item record

Page view(s)

checked on Apr 3, 2023

Google ScholarTM


Add Files to Item

Note about this record

Cite this record


Items in TORE are protected by copyright, with all rights reserved, unless otherwise indicated.