Artificial neural networks for inverse design of resonant nanophotonic components with oscillatory loss landscapes

Lenaerts, Joeri; Pinson, Hannah; Ginis, Vincent

doi:10.1515/nanoph-2020-0379

Cited by 11 publications

(6 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Typically, the absolute prediction error of the conventional network is relatively remarkable around the sharp spectral dip features (e.g., high Q optical responses). One might increase the spectral sampling points to lower the absolute prediction error in a conventional network, [ 36 ] but this would inevitably take more calculation time and hardware resources in the simulation and training process. By adopting the scheme of divide‐and‐conquer DL, we do not have to increase the spectral sampling points, and depress the absolute errors around the sharp spectral dips dramatically as denoted in the gray dashed frames of these figures.…”

Section: Resultsmentioning

confidence: 99%

Real‐Time On‐Demand Design of Circuit‐Analog Plasmonic Stack Metamaterials by Divide‐and‐Conquer Deep Learning

Xiong

Shen

Gao

et al. 2022

Laser & Photonics Reviews

View full text Add to dashboard Cite

The design of plasmonic stack metamaterials (PSMs) is critical due to their promising potentials in the fields of optical absorbers, sensors, and thermal irradiation. Compared with the classical circuit‐based optimization, the design by deep learning (DL) has attracted greater attention, since it is not essential to obtain their equivalent circuit parameters. Currently, a DL model for their higher‐precision design, especially with complicated spectral features, is still quite in demand. Here, a divide‐and‐conquer DL model based on a bidirectional artificial neural network is proposed. As proof‐of‐concept examples, the PSMs consisting of two metal/dielectric/metal/dielectric subwavelength stacks are adopted to demonstrate the validity of the paradigm. It demonstrates a significant prediction error reduction of 37.5% with the 47.8% decrease of training parameters than the conventional method in the forward network, which supports a powerful inverse design from spectra to PSM structures. Furthermore, a flexible tool based on the free customer definition, which facilitates the real‐time design of PSMs with various circuit‐analog functions, is developed. The fabrication and measurement experiments verify the design performance of the method. The study enhances the precision and convenience of on‐demand circuit‐analog PSMs and will provide a guide for fast high‐performance inverse design of many other metamaterials.

show abstract

Section: Resultsmentioning

confidence: 99%

Real‐Time On‐Demand Design of Circuit‐Analog Plasmonic Stack Metamaterials by Divide‐and‐Conquer Deep Learning

Xiong

Shen

Gao

et al. 2022

Laser & Photonics Reviews

View full text Add to dashboard Cite

show abstract

“…A NN model was developed to optimize transmission and reflection from the Fabry–Perot resonator and Bragg reflectors . The input parameters included the Finesse coefficient and the phase difference between transmitted partial waves.…”

Section: Physics and Design Methodologiesmentioning

confidence: 99%

“…A NN model was developed to optimize transmission and reflection from the Fabry−Perot resonator and Bragg reflectors. 200 The input parameters included the Finesse coefficient and the phase difference between transmitted partial waves. They significantly improved the NN model's efficiency by adding the Fourier transform of the desired spectrum to the optimization procedure.…”

Section: Physics and Design Methodologiesmentioning

confidence: 99%

Recent Advances in Tunable Metasurfaces: Materials, Design, and Applications

et al. 2022

View full text Add to dashboard Cite

Metasurfaces, a two-dimensional (2D) form of metamaterials constituted by planar meta-atoms, exhibit exotic abilities to tailor electromagnetic (EM) waves freely. Over the past decade, tremendous efforts have been made to develop various active materials and incorporate them into functional devices for practical applications, pushing the research of tunable metasurfaces to the forefront of nanophotonics. Those active materials include phase change materials (PCMs), semiconductors, transparent conducting oxides (TCOs), ferroelectrics, liquid crystals (LCs), atomically thin material, etc., and enable intriguing performances such as fast switching speed, large modulation depth, ultracompactness, and significant contrast of optical properties under external stimuli. Integration of such materials offers substantial tunability to the conventional passive nanophotonic platforms. Tunable metasurfaces with multifunctionalities triggered by various external stimuli bring in rich degrees of freedom in terms of material choices and device designs to dynamically manipulate and control EM waves on demand. This field has recently flourished with the burgeoning development of physics and design methodologies, particularly those assisted by the emerging machine learning (ML) algorithms. This review outlines recent advances in tunable metasurfaces in terms of the active materials and tuning mechanisms, design methodologies, and practical applications. We conclude this review paper by providing future perspectives in this vibrant and fast-growing research field.

show abstract

“…To make this possible, a large arsenal of different reflective mode converters needs to be designed. In this design, there is an important role for inverse design techniques, which have recently become much more powerful through the incorporation of machine learning techniques [52].…”

Section: Advances In Science and Technology To Meet Challengesmentioning

confidence: 99%

Roadmap on multimode light shaping

Piccardo¹,

Ginis²,

Forbes³

et al. 2021

J. Opt.

Self Cite

View full text Add to dashboard Cite

Our ability to generate new distributions of light has been remarkably enhanced in recent years. At the most fundamental level, these light patterns are obtained by ingeniously combining different electromagnetic modes. Interestingly, the modal superposition occurs in the spatial, temporal as well as spatio-temporal domain. This generalized concept of structured light is being applied across the entire spectrum of optics: generating classical and quantum states of light, harnessing linear and nonlinear light-matter interactions, and advancing applications in microscopy, spectroscopy, holography, communication, and synchronization. This Roadmap highlights the common roots of these different techniques and thus establishes links between research areas that complement each other seamlessly. We provide an overview of all these areas, their backgrounds, current research, and future developments. We highlight the power of multimodal light manipulation and want to inspire new eclectic approaches in this vibrant research community.

show abstract

Artificial neural networks for inverse design of resonant nanophotonic components with oscillatory loss landscapes

Cited by 11 publications

References 40 publications

Real‐Time On‐Demand Design of Circuit‐Analog Plasmonic Stack Metamaterials by Divide‐and‐Conquer Deep Learning

Real‐Time On‐Demand Design of Circuit‐Analog Plasmonic Stack Metamaterials by Divide‐and‐Conquer Deep Learning

Recent Advances in Tunable Metasurfaces: Materials, Design, and Applications

Roadmap on multimode light shaping

Contact Info

Product

Resources

About