New publication from Opto-Electronic Advances; DOI 10.29026 / oea.2022.210147 reviews the evaluation of metaphotonics induced by artificial intelligence and provides a summary of machine learning concepts with some specific examples developed and demonstrated for metasystems and metaserface.
As a result of advances in the field of artificial intelligence, these technologies have been incorporated into the scientific research process and into the field of photonics. Techniques such as machine learning and deep learning have become popular design tools for the development of photonic devices. Design in this case refers to the reverse process of estimating the physical response of a given structure (forward design) as well as finding the parameters of the structure required to provide the desired response (inverse design). Although design approaches are undoubtedly the most widespread implementation of machine learning in photonics, novel applications are beginning to emerge, which will lead to the evolution of a new research area. Intelligent photonics.
The authors of this article review recent developments in the field of intelligent metaphotonics. This subfield of photonics is called structural subwavelength nanoparticles (commonly known as Meta-molecules) The review covers machine learning for the design of such devices as well as other uses of machine learning, including classification tools, control systems, and feedback mechanisms. Particular attention is paid to potential practical applications, including solar cells, biosensors or imagers. Without diving into a detailed description of the methods, the authors intertwined the various aspects of machine learning and metaphotonics, building a broad and coherent picture of their interaction, highlighting the specifics of the intellectual systems. Novel concepts such as self-adapting systems or intelligent biosensors are introduced and discussed in the context of the future development of metaphotonics. Under self-adaptation the authors refer to devices capable of automatically tuning their responses to changes in environmental conditions. One of the examples provided is the adjustment of a garment to changes in the frequency and angle of incidence of the electromagnetic field, which allows to preserve operation under a wide range of conditions. The concept of intelligent biosensors refers to the use of machine learning as a tool for the classification of models. The review emphasizes the importance of metaphotonics for artificial intelligence, which exemplifies many examples of metaserface used as platforms for the al-optical realization of machine learning algorithms.
For a wider audience, a review may be interesting, such as an introduction to the field of intelligent metaphotonics and an overview of its state of the art. The authors provide a brief overview of the ideas behind ML and avoid technical details so no specific knowledge of computer science is required. The paper provides detailed explanations of emerging concepts to introduce readers to the novel direction of photonics development and consequently to provide hints for in-depth studies.
The authors of this article have reviewed this field Intelligent metaphotonics – Science area at the junction of Artificial Intelligence (AI) and Metaphotonics.
AI is rapidly becoming a part of everyday work and daily life around the world. Recent advances in this area have been made possible by the development of a concept such as machine learning (ML), which represents a set of data-based algorithms for AI’s learning ability. ML allows the computer to learn from experience which means that with an increased amount of input data the program can better perform its aforementioned tasks. Repetitions and trainings in the same manner improve human performance, while learning approaches and abilities vary greatly.
Science does not shy away from modern trends and does not adopt advanced methods of computer science for problem solving and development of novel concepts. This article focuses on the application of ML in metaphotonics – the evolving region of subwavelength photonics induced by the physics of metamaterials. Introduced initially as a tool for forward and inverse design of photonic systems, ML has already evolved into a larger than one method for design. Provides review examples of how ML is embedded as a support tool for feedback and control mechanism of photonic sensors or self-adapting systems. Without a doubt ML is rapidly becoming a powerful tool for research in the field of metaphotonics. The merging of these two areas has developed a new area of research commonly known as Intelligent metaphotonics It usually refers to metaphotonic systems designed or enhanced with ML or AI.
The article provides a brief introduction to AI concepts, ML is considered a “black-box” throughout the paper, giving the expected result without any specific details on exactly how it was achieved. Such an approach allows authors to focus on specific metaphotonic systems and their applications initiated by ML rather than on specific methods and algorithms. Also, the paper may be interesting in this way for readers unfamiliar with computer science. After introduction, the paper covers the ML-auxiliary design of nanoAntennae that build up metaphotonic structures. Then, the focus shifts to improving their properties with transformative metaserface and ML. Particular attention is paid to potential real-world applications such as structured colors, LIDARs or close-up displays. Metaserface applications as platforms for biosensing are presented in a separate section because ML can be used not only as a design method but also as a tool for classifying models in this field. This idea is presented with examples of sensors for the SARS-CoV-2 classification And for monitoring biomolecular dynamics. Another class of applications consists of self-adapting devices – metaphotonic systems that automatically adapt to environmental changes and adjust their responses. Examples provided include self-adapting microwave clocks and imagers as well as metaphotonic systems used as computational platforms for ML. Finally, the authors provide a perspective that covers emerging and potential trends in the field of intelligent metaphotonics, assuming not only the effect of ML on photonics but also the vice versa importance of photonics to AI technologies.
Article reference: Krasikov S, Tranter A, Bogdanov A, Kiwishar Y. Intelligent Metaphotonics Powered by Machine Learning. Opto-Electron Adv 5, 210147 (2022). 10.29026 / oea.2022.210147
Keywords: Metaphotonics; Machine learning; Artificial intelligence
The research was led by Professor Yuri Kiwishar, a world leader in photonics and metamaterials and one of the founders of the field of all – dielectric resonant metaphotonics, which is governed by the physics of your resonance in dielectric nanoparticles with a high refractive index.
Opto-Electronic Advances (OEA) is a high-impact, open-access, peer-reviewed monthly SCI journal with an impact of 9.682 (Journal citation reports for IF 2020). Since its launch in March 2018, the OEA has been indexed over time into the SCI, EI, DOAJ, Scopus, CA and ICI databases and expanded its editorial board to 36 members from 17 countries and regions (average h-index 49).
The Journal is published by The Chinese Academy of Sciences, The Institute of Optics and Electronics, with the aim of providing a platform for researchers, educators, professionals, practitioners and students to present and share knowledge in the form of high quality empirical and theoretical research papers. Elements of optics, photonics and optoelectronics.
More info: http://www.oejournal.org/oea
Editorial Board: http://www.oejournal.org/oea/editorialboard/list
All issues are available in the online archive (http://www.oejournal.org/oea/archive).
Submissions to OAS Can be made using ScholarOne (https://mc03.manuscriptcentral.com/oea).
CN: 51-1781 / TN
Contact us: email@example.com
Twitter: @OptoElectronAdv (https://twitter.com/OptoElectronAdv?lang=en)
WeChat: OE_ Journal
Disclaimer: AAAS and EurekAlert! They are not responsible for the accuracy of news releases posted to EurekAlert! By providing organizations or by using any information through the Eurekalert system.