scispace - formally typeset
Search or ask a question
Author

Yixuan Tan

Bio: Yixuan Tan is an academic researcher from University of Wisconsin-Madison. The author has contributed to research in topics: Inverse scattering problem & Chemistry. The author has an hindex of 5, co-authored 11 publications receiving 455 citations. Previous affiliations of Yixuan Tan include Wisconsin Alumni Research Foundation.

Papers
More filters
Journal ArticleDOI
TL;DR: A tandem neural network architecture is demonstrated that tolerates inconsistent training instances in inverse design of nanophotonic devices and provides a way to train large neural networks for the inverseDesign of complex photonic structures.
Abstract: Data inconsistency leads to a slow training process when deep neural networks are used for the inverse design of photonic devices, an issue that arises from the fundamental property of nonuniqueness in all inverse scattering problems. Here we show that by combining forward modeling and inverse design in a tandem architecture, one can overcome this fundamental issue, allowing deep neural networks to be effectively trained by data sets that contain nonunique electromagnetic scattering instances. This paves the way for using deep neural networks to design complex photonic structures that require large training data sets.

619 citations

Proceedings ArticleDOI
05 May 2019
TL;DR: In this article, a tandem neural network architecture is proposed to tolerate inconsistent training instances in inverse design of nanophotonic devices, which provides a way to train large neural networks for the inverse design complex photonic structures.
Abstract: We demonstrate a tandem neural network architecture that tolerates inconsistent training instances in inverse design of nanophotonic devices. It provides a way to train large neural networks for the inverse design of complex photonic structures. © 2019 The Author(s)

199 citations

Journal ArticleDOI
TL;DR: In this article, the authors proposed and experimentally demonstrated a completely different mechanism to achieve spectrally selective metallic emitters based on a tunneling effect, which allowed a simple flat metal film to achieve a near-unity emissivity with controlled spectral selectivity for efficient heat-to-light energy conversion.
Abstract: Infrared thermal emission from metals has important energy applications in thermophotovoltaics, radiative cooling, and lighting. Unfortunately, the emissivity of flat metal films is close to zero because the screening effect prevents metals' fluctuating currents from emitting to the far field. As a result, metal films are often used as reflecting mirrors instead of thermal emitters. Recently, nanostructured metals, such as metamaterials, have emerged as an interesting way to enhance and to spectrally control thermal emission based on plasmonic resonant effects. However, they require sophisticated lithography. Here, we proposed and experimentally demonstrated a completely different mechanism to achieve spectrally selective metallic emitters based on a tunneling effect. This effect allows a simple flat metal film to achieve a near-unity emissivity with controlled spectral selectivity for efficient heat-to-light energy conversion.

49 citations

Proceedings ArticleDOI
15 Jun 2019
TL;DR: Zhang et al. as mentioned in this paper introduced a novel approach based on speckle pattern recognition with deep neural network, which is simpler and more robust than other NLOS recognition methods.
Abstract: Visual object recognition under situations in which the direct line-of-sight is blocked, such as when it is occluded around the corner, is of practical importance in a wide range of applications. With coherent illumination, the light scattered from diffusive walls forms speckle patterns that contain information of the hidden object. It is possible to realize non-line-of-sight (NLOS) recognition with these speckle patterns. We introduce a novel approach based on speckle pattern recognition with deep neural network, which is simpler and more robust than other NLOS recognition methods. Simulations and experiments are performed to verify the feasibility and performance of this approach.

17 citations

Journal ArticleDOI
TL;DR: In this paper, a thermal extractor is proposed to convert and guide the near-field energy to the far field, where it transforms the nearfield energy and sends it toward the far-field.
Abstract: Abstract Thermal radiation plays an increasingly important role in many emerging energy technologies, such as thermophotovoltaics, passive radiative cooling and wearable cooling clothes [1]. One of the fundamental constraints in thermal radiation is the Stefan-Boltzmann law, which limits the maximum power of far-field radiation to P0 = σT4S, where σ is the Boltzmann constant, S and T are the area and the temperature of the emitter, respectively (Fig. 1a). In order to overcome this limit, it has been shown that near-field radiations could have an energy density that is orders of magnitude greater than the Stefan-Boltzmann law [2-7]. Unfortunately, such near-field radiation transfer is spatially confined and cannot carry radiative heat to the far field. Recently, a new concept of thermal extraction was proposed [8] to enhance far-field thermal emission, which, conceptually, operates on a principle similar to oil immersion lenses and light extraction in light-emitting diodes using solid immersion lens to increase light output [62].Thermal extraction allows a blackbody to radiate more energy to the far field than the apparent limit of the Stefan-Boltzmann law without breaking the second law of thermodynamics. Thermal extraction works by using a specially designed thermal extractor to convert and guide the near-field energy to the far field, as shown in Fig. 1b. The same blackbody as shown in Fig. 1a is placed closely below the thermal extractor with a spacing smaller than the thermal wavelength. The near-field coupling transfers radiative energy with a density greater than σT4. The thermal extractor, made from transparent and high-index or structured materials, does not emit or absorb any radiation. It transforms the near-field energy and sends it toward the far field. As a result, the total amount of far-field radiative heat dissipated by the same blackbody is greatly enhanced above SσT4, where S is the area of the emitter. This paper will review the progress in thermal extraction. It is organized as follows. In Section 1, we will discuss the theory of thermal extraction [8]. In Section 2, we review an experimental implementation based on natural materials as the thermal extractor [8]. Lastly, in Section 3, we review the experiment that uses structured metamaterials as thermal extractors to enhance optical density of states and far-field emission [9].

13 citations


Cited by
More filters
Journal ArticleDOI
01 Jun 2018-ACS Nano
TL;DR: A deep-learning-based model is reported, comprising two bidirectional neural networks assembled by a partial stacking strategy, to automatically design and optimize three-dimensional chiral metamaterials with strong chiroptical responses at predesignated wavelengths.
Abstract: Deep-learning framework has significantly impelled the development of modern machine learning technology by continuously pushing the limit of traditional recognition and processing of images, speech, and videos. In the meantime, it starts to penetrate other disciplines, such as biology, genetics, materials science, and physics. Here, we report a deep-learning-based model, comprising two bidirectional neural networks assembled by a partial stacking strategy, to automatically design and optimize three-dimensional chiral metamaterials with strong chiroptical responses at predesignated wavelengths. The model can help to discover the intricate, nonintuitive relationship between a metamaterial structure and its optical responses from a number of training examples, which circumvents the time-consuming, case-by-case numerical simulations in conventional metamaterial designs. This approach not only realizes the forward prediction of optical performance much more accurately and efficiently but also enables one to i...

619 citations

Journal ArticleDOI
TL;DR: In this paper, artificial neural networks are used to approximate light scattering by multilayer nanoparticles. But the network needs to be trained on only a small sampling of the data to approximate the simulation to high precision.
Abstract: We propose a method to use artificial neural networks to approximate light scattering by multilayer nanoparticles. We find that the network needs to be trained on only a small sampling of the data to approximate the simulation to high precision. Once the neural network is trained, it can simulate such optical processes orders of magnitude faster than conventional simulations. Furthermore, the trained neural network can be used to solve nanophotonic inverse design problems by using back propagation, where the gradient is analytical, not numerical.

576 citations

Journal ArticleDOI
TL;DR: This work identifies a solution to circumvent this conventional design procedure by means of a deep learning architecture to expedite the discovery and design of metasurfaces for tailored optical responses in a systematic, inverse-design manner.
Abstract: The advent of metasurfaces in recent years has ushered in a revolutionary means to manipulate the behavior of light on the nanoscale. The design of such structures, to date, has relied on the expertise of an optical scientist to guide a progression of electromagnetic simulations that iteratively solve Maxwell's equations until a locally optimized solution can be attained. In this work, we identify a solution to circumvent this conventional design procedure by means of a deep learning architecture. When fed an input set of customer-defined optical spectra, the constructed generative network generates candidate patterns that match the on-demand spectra with high fidelity. This approach reveals an opportunity to expedite the discovery and design of metasurfaces for tailored optical responses in a systematic, inverse-design manner.

536 citations

Journal ArticleDOI
TL;DR: Recent progress in deep-learning-based photonic design is reviewed by providing the historical background, algorithm fundamentals and key applications, with the emphasis on various model architectures for specific photonic tasks.
Abstract: Innovative approaches and tools play an important role in shaping design, characterization and optimization for the field of photonics. As a subset of machine learning that learns multilevel abstraction of data using hierarchically structured layers, deep learning offers an efficient means to design photonic structures, spawning data-driven approaches complementary to conventional physics- and rule-based methods. Here, we review recent progress in deep-learning-based photonic design by providing the historical background, algorithm fundamentals and key applications, with the emphasis on various model architectures for specific photonic tasks. We also comment on the challenges and perspectives of this emerging research direction. The application of deep learning to the design of photonic structures and devices is reviewed, including algorithm fundamentals.

446 citations

Journal ArticleDOI
Wei Ma1, Feng Cheng1, Yihao Xu1, Qinlong Wen1, Yongmin Liu1 
TL;DR: This work proposes to represent metamaterials and model the inverse design problem in a probabilistically generative manner, enabling to elegantly investigate the complex structure–performance relationship in an interpretable way, and solve the one‐to‐many mapping issue that is intractable in a deterministic model.
Abstract: The research of metamaterials has achieved enormous success in the manipulation of light in a prescribed manner using delicately designed subwavelength structures, so-called meta-atoms. Even though modern numerical methods allow for the accurate calculation of the optical response of complex structures, the inverse design of metamaterials, which aims to retrieve the optimal structure according to given requirements, is still a challenging task owing to the nonintuitive and nonunique relationship between physical structures and optical responses. To better unveil this implicit relationship and thus facilitate metamaterial designs, it is proposed to represent metamaterials and model the inverse design problem in a probabilistically generative manner, enabling to elegantly investigate the complex structure-performance relationship in an interpretable way, and solve the one-to-many mapping issue that is intractable in a deterministic model. Moreover, to alleviate the burden of numerical calculations when collecting data, a semisupervised learning strategy is developed that allows the model to utilize unlabeled data in addition to labeled data in an end-to-end training. On a data-driven basis, the proposed deep generative model can serve as a comprehensive and efficient tool that accelerates the design, characterization, and even new discovery in the research domain of metamaterials, and photonics in general.

333 citations