Inverse design of nanophotonics devices and materials

Wiecha, Peter R.; Petrov, Alexander Yu.; Genevet, Patrice; Bogdanov, Andrey

doi:10.1016/j.photonics.2022.101084

Cited by 11 publications

(2 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Deep learning is a rapidly growing field that has revolutionized various domains, including nanophotonic device design. [6][7][8][9][10][11][11][12][13][14][15][16][17] In recent years, generative deep neural networks have achieved significant advancements, evident in technologies like ChatGPT and high-quality image generation. They are also being applied to inverse design of nanophotonic devices 6,9,18,19 Our research centers on enhancing a specific generative deep learning model, the conditional autoencoder, which is a vital part of the generative deep learning architecture.…”

Section: Introductionmentioning

confidence: 99%

Enhancing inverse design of nanophotonic devices through generative deep learning, Bayesian latent optimization, and transfer learning

Kojima

2024

AI and Optical Data Sciences V

View full text Add to dashboard Cite

In recent years, generative AI has made remarkable strides, enabling the creation of exceptional quality novel designs and images. This study aims to enhance the performance of a conditional autoencoder, a type of generative deep learning framework. Our primary focus lies in applying these techniques to improve the design of metagratings. By harnessing the power of generative modeling and Bayesian optimization, we can generate optimized designs for metagratings, thereby enhancing their functionality and efficiency. Additionally, through the use of transfer learning, we adapt the network originally designed for transverse-electric (TE) modes to encompass transverse-magnetic (TM) modes. This adaptation spans a wide range of deflection angles and operating wavelengths, with minimal additional training data required. This versatile black-box approach has broad applications in the inverse design of various photonic and nanophotonic devices.

show abstract

Section: Introductionmentioning

confidence: 99%

Enhancing inverse design of nanophotonic devices through generative deep learning, Bayesian latent optimization, and transfer learning

Kojima

2024

AI and Optical Data Sciences V

View full text Add to dashboard Cite

show abstract

“…However, even the most data-efficient models can not offset the cost of data generation if the problem at hand requires only a handful of simulations in the first place. Therefore, we identify inverse design, − specifically gradient-based, as a discipline that is well-suited to benefit from the speed of surrogate models and suffers little from their drawbacks. , In gradient-based inverse design, a functional element is optimized by incrementally maximizing some figure of merit. Gradients of this figure of merit with respect to incremental changes in the geometry are then used to refine the device until an optimum is found iteratively.…”

Section: Introductionmentioning

confidence: 99%

Neural Operator-Based Surrogate Solver for Free-Form Electromagnetic Inverse Design

2023

View full text Add to dashboard Cite

Neural operators have emerged as a powerful tool for solving partial differential equations in the context of scientific machine learning. Here, we implement and train a modified Fourier neural operator as a surrogate solver for electromagnetic scattering problems and compare its data efficiency to existing methods. We further demonstrate its application to the gradient-based nanophotonic inverse design of free-form, fully three-dimensional electromagnetic scatterers, an area that has so far eluded the application of deep-learning techniques.

show abstract