Improved inverse design of polarization splitter with advanced Bayesian optimization DOI
Chao Xu, Tingge Dai,

H. Y. Wei

и другие.

Optics Communications, Год журнала: 2024, Номер 575, С. 131272 - 131272

Опубликована: Ноя. 10, 2024

Язык: Английский

Large-scale photonic inverse design: computational challenges and breakthroughs DOI Creative Commons
Chanik Kang, Chaejin Park, Myunghoo Lee

и другие.

Nanophotonics, Год журнала: 2024, Номер 13(20), С. 3765 - 3792

Опубликована: Июнь 6, 2024

Abstract Recent advancements in inverse design approaches, exemplified by their large-scale optimization of all geometrical degrees freedom, have provided a significant paradigm shift photonic design. However, these innovative strategies still require full-wave Maxwell solutions to compute the gradients concerning desired figure merit, imposing, prohibitive computational demands on conventional computing platforms. This review analyzes challenges associated with structures. It delves into adequacy various electromagnetic solvers for designs, from neural network-based solvers, and discusses suitability limitations. Furthermore, this evaluates research techniques, advantages disadvantages applications, sheds light cutting-edge studies that combine networks applications. Through comprehensive examination, aims provide insights navigating landscape advocate strategic methods, solver selection, integration overcome barriers, thereby guiding future

Язык: Английский

Процитировано

8

Recent Advances in Electromagnetic Devices: Design and Optimization DOI Creative Commons
Chanik Kang, Haejun Chung

Micromachines, Год журнала: 2025, Номер 16(1), С. 98 - 98

Опубликована: Янв. 16, 2025

Electromagnetic devices are a continuous driving force in cutting-edge research and technology, finding applications diverse fields such as optics [...]

Язык: Английский

Процитировано

1

Inverse design of color routers in CMOS image sensors: toward minimizing interpixel crosstalk DOI Creative Commons
Sangbin Lee,

Jaehyun Hong,

J.S. Kang

и другие.

Nanophotonics, Год журнала: 2024, Номер 13(20), С. 3895 - 3914

Опубликована: Июль 1, 2024

Abstract Over the past decade, significant advancements in high-resolution imaging technology have been driven by miniaturization of pixels within image sensors. However, this reduction pixel size to submicrometer dimensions has led decreased efficiency color filters and microlens arrays. The development routers that operate at visible wavelengths presents a promising avenue for further miniaturization. Despite this, existing often encounter severe interpixel crosstalk, around 70 %, due reliance on periodic boundary conditions. Here, we present crosstalk-minimized achieve an unprecedented in-pixel optical 87.2 % significantly reduce crosstalk 2.6 %. are designed through adjoint optimization, incorporating customized incident waves minimize crosstalks. Our findings suggest our router design surpasses routing techniques terms efficiency, representing crucial step forward push toward commercializing next generation solid-state

Язык: Английский

Процитировано

5

Revolutionary Integration of Artificial Intelligence with Meta-Optics-Focus on Metalenses for Imaging DOI Creative Commons
Nikolay L. Kazanskiy, Svetlana N. Khonina, Ivan Oseledets

и другие.

Technologies, Год журнала: 2024, Номер 12(9), С. 143 - 143

Опубликована: Авг. 28, 2024

Artificial intelligence (AI) significantly enhances the development of Meta-Optics (MOs), which encompasses advanced optical components like metalenses and metasurfaces designed to manipulate light at nanoscale. The intricate design these requires sophisticated modeling optimization achieve precise control over behavior, tasks for AI is exceptionally well-suited. Machine learning (ML) algorithms can analyze extensive datasets simulate numerous variations identify most effective configurations, drastically speeding up process. also enables adaptive MOs that dynamically adjust changing imaging conditions, improving performance in real-time. This results superior image quality, higher resolution, new functionalities across various applications, including microscopy, medical diagnostics, consumer electronics. combination with thus epitomizes a transformative advancement, pushing boundaries what possible technology. In this review, we explored latest advancements AI-powered applications.

Язык: Английский

Процитировано

5

Deep Learning Design for Loss Optimization in Metamaterials DOI Creative Commons
Xianfeng Wu, Zhao Jing,

Kunlun Xie

и другие.

Nanomaterials, Год журнала: 2025, Номер 15(3), С. 178 - 178

Опубликована: Янв. 23, 2025

Inherent material loss is a pivotal challenge that impedes the development of metamaterial properties, particularly in context 3D metamaterials operating at visible wavelengths. Traditional approaches, such as design periodic model structures and selection noble metals, have encountered plateau. Coupled with complexities constructing achieving precise alignment, these factors made creation low-loss spectrum formidable task. In this work, we harness concept deep learning, combined principle weak interactions metamaterials, to re-examine optimize previously validated disordered discrete metamaterials. The paper presents an innovative strategy for optimization structural unit distributions, proving their robustness ability perform intended functions within critical distribution ratio. This refined offers theoretical framework single-frequency broadband systems. It paves way optical facile fabrication high-performance photonic devices.

Язык: Английский

Процитировано

0

Inverse design of photonic surfaces via multi fidelity ensemble framework and femtosecond laser processing DOI Creative Commons
Luka Grbčić, Minok Park, Mahmoud Elzouka

и другие.

npj Computational Materials, Год журнала: 2025, Номер 11(1)

Опубликована: Фев. 15, 2025

We demonstrate a multi-fidelity (MF) machine learning ensemble framework for the inverse design of photonic surfaces, trained on dataset 11,759 samples that we fabricate using high throughput femtosecond laser processing. The MF combines an initial low fidelity model generating solutions, with refines these solutions through local optimization. combined can generate multiple disparate sets laser-processing parameters each produce same target input spectral emissivity accuracy (root mean squared errors < 2%). SHapley Additive exPlanations analysis shows transparent interpretability complex relationship between and emissivity. Finally, is experimentally validated by fabricating evaluating surface designs it generates improved efficiency energy harvesting devices. Our approach provides powerful tool advancing surfaces in applications.

Язык: Английский

Процитировано

0

Learning thermoacoustic interactions in combustors using a physics-informed neural network DOI
Sathesh Mariappan, Kamaljyoti Nath, George Em Karniadakis

и другие.

Engineering Applications of Artificial Intelligence, Год журнала: 2024, Номер 138, С. 109388 - 109388

Опубликована: Окт. 4, 2024

Язык: Английский

Процитировано

2

Adjoint Method-based Fourier Neural Operator Surrogate Solver for Wavefront Shaping in Tunable Metasurfaces DOI Creative Commons
Chanik Kang,

Joonhyuk Seo,

Ikbeom Jang

и другие.

iScience, Год журнала: 2024, Номер 28(1), С. 111545 - 111545

Опубликована: Дек. 6, 2024

Язык: Английский

Процитировано

1

Improved inverse design of polarization splitter with advanced Bayesian optimization DOI
Chao Xu, Tingge Dai,

H. Y. Wei

и другие.

Optics Communications, Год журнала: 2024, Номер 575, С. 131272 - 131272

Опубликована: Ноя. 10, 2024

Язык: Английский

Процитировано

0