1
|
Davey CP, Shakeel I, Deo RC, Salcedo-Sanz S. Deep Learning Based Over-the-Air Training of Wireless Communication Systems without Feedback. SENSORS (BASEL, SWITZERLAND) 2024; 24:2993. [PMID: 38793848 PMCID: PMC11125374 DOI: 10.3390/s24102993] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 03/14/2024] [Revised: 04/19/2024] [Accepted: 05/06/2024] [Indexed: 05/26/2024]
Abstract
In trainable wireless communications systems, the use of deep learning for over-the-air training aims to address the discontinuity in backpropagation learning caused by the channel environment. The primary methods supporting this learning procedure either directly approximate the backpropagation gradients using techniques derived from reinforcement learning, or explicitly model the channel environment by training a generative channel model. In both cases, over-the-air training of transmitter and receiver requires a feedback channel to sound the channel environment and obtain measurements of the learning objective. The use of continuous feedback not only demands extra system resources but also makes the training process more susceptible to adversarial attacks. Conversely, opting for a feedback-free approach to train the models over the forward link, exclusively on the receiver side, could pose challenges to reliably end the training process without intermittent testing over the actual channel environment. In this article, we propose a novel method for the over-the-air training of wireless communication systems that does not require a feedback channel to train the transmitter and receiver. Random samples are transmitted through the channel environment to train a mixture density network to approximate the channel distribution on the receiver side of the network. The transmitter and receiver models are trained with the resulting channel model, and the transmitter can be deployed after training. We show that the block error rate measurements obtained with the simulated channel are suitable for monitoring as a stopping criterion during the training process. The resulting method is demonstrated to have equivalent performance to the end-to-end autoencoder training on small message sequences.
Collapse
Affiliation(s)
- Christopher P. Davey
- School of Mathematics, Physics and Computing, University of Southern Queensland, Springfield, QLD 4300, Australia
| | - Ismail Shakeel
- Spectrum Warfare Branch, Information Sciences Division, Defence Science and Technology Group (DSTG), Edinburgh, SA 5111, Australia;
| | - Ravinesh C. Deo
- School of Mathematics, Physics and Computing, University of Southern Queensland, Springfield, QLD 4300, Australia
| | - Sancho Salcedo-Sanz
- Department of Signal Processing and Communications, Universidad de Alcalá, 28805 Alcalá de Henares, Madrid, Spain;
| |
Collapse
|
2
|
Adibnia E, Mansouri-Birjandi MA, Ghadrdan M, Jafari P. A deep learning method for empirical spectral prediction and inverse design of all-optical nonlinear plasmonic ring resonator switches. Sci Rep 2024; 14:5787. [PMID: 38461205 PMCID: PMC10924975 DOI: 10.1038/s41598-024-56522-3] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/28/2023] [Accepted: 03/07/2024] [Indexed: 03/11/2024] Open
Abstract
All-optical plasmonic switches (AOPSs) utilizing surface plasmon polaritons are well-suited for integration into photonic integrated circuits (PICs) and play a crucial role in advancing all-optical signal processing. The current AOPS design methods still rely on trial-and-error or empirical approaches. In contrast, recent deep learning (DL) advances have proven highly effective as computational tools, offering an alternative means to accelerate nanophotonics simulations. This paper proposes an innovative approach utilizing DL for spectrum prediction and inverse design of AOPS. The switches employ circular nonlinear plasmonic ring resonators (NPRRs) composed of interconnected metal-insulator-metal waveguides with a ring resonator. The NPRR switching performance is shown using the nonlinear Kerr effect. The forward model presented in this study demonstrates superior computational efficiency when compared to the finite-difference time-domain method. The model analyzes various structural parameters to predict transmission spectra with a distinctive dip. Inverse modeling enables the prediction of design parameters for desired transmission spectra. This model provides a rapid estimation of design parameters, offering a clear advantage over time-intensive conventional optimization approaches. The loss of prediction for both the forward and inverse models, when compared to simulations, is exceedingly low and on the order of 10-4. The results confirm the suitability of employing DL for forward and inverse design of AOPSs in PICs.
Collapse
Affiliation(s)
- Ehsan Adibnia
- Faculty of Electrical and Computer Engineering, University of Sistan and Baluchestan (USB), P.O. Box 9816745563, Zahedan, Iran
| | - Mohammad Ali Mansouri-Birjandi
- Faculty of Electrical and Computer Engineering, University of Sistan and Baluchestan (USB), P.O. Box 9816745563, Zahedan, Iran.
| | - Majid Ghadrdan
- Faculty of Electrical and Computer Engineering, University of Sistan and Baluchestan (USB), P.O. Box 9816745563, Zahedan, Iran
| | - Pouria Jafari
- Faculty of Electrical and Computer Engineering, University of Sistan and Baluchestan (USB), P.O. Box 9816745563, Zahedan, Iran
| |
Collapse
|
3
|
Yu S, Zhang T, Dai J, Xu K. Hybrid inverse design scheme for nanophotonic devices based on encoder-aided unsupervised and supervised learning. OPTICS EXPRESS 2023; 31:39852-39866. [PMID: 38041299 DOI: 10.1364/oe.505089] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Received: 09/05/2023] [Accepted: 10/30/2023] [Indexed: 12/03/2023]
Abstract
Machine learning methods have been regarded as practical tools for the inverse design of nanophotonic devices. However, for the devices with complex expected targets, such as the spectrum with multiple peaks and valleys, there are still many sufferings remaining for these data-driven approaches, such as overfitting. To resolve it, we firstly propose a hybrid inverse design scheme combining supervised and unsupervised learning. Compared with the previous inverse design schemes based on artificial neural networks (ANNs), clustering algorithms and an encoder model are introduced for data preprocessing. A typical metamaterial composed of multiple metal strips that can produce tunable dual plasmon-induced transparency phenomena is designed to verify the performance of our proposed hybrid scheme. Compared with the ANNs directly trained by the entire dataset, the loss functions (mean squared error) of the ANNs in our hybrid scheme can be effectively reduced by more than 51% for both training and test datasets under the same training conditions. Our hybrid scheme paves an efficient improvement for the inverse design tasks with complex targets.
Collapse
|
4
|
He X, Cui X, Chan CT. Constrained tandem neural network assisted inverse design of metasurfaces for microwave absorption. OPTICS EXPRESS 2023; 31:40969-40979. [PMID: 38041384 DOI: 10.1364/oe.506936] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Received: 10/02/2023] [Accepted: 11/03/2023] [Indexed: 12/03/2023]
Abstract
Designing microwave absorbers with customized spectrums is an attractive topic in both scientific and engineering communities. However, due to the massive number of design parameters involved, the design process is typically time-consuming and computationally expensive. To address this challenge, machine learning has emerged as a powerful tool for optimizing design parameters. In this work, we present an analytical model for an absorber composed of a multi-layered metasurface and propose a novel inverse design method based on a constrained tandem neural network. The network can provide structural and material parameters optimized for a given absorption spectrum, without requiring professional knowledge. Furthermore, additional physical attributes, such as absorber thickness, can be optimized when soft constraints are applied. As an illustrative example, we use the neural network to design broadband microwave absorbers with a thickness close to the causality limit imposed by the Kramers-Kronig relation. Our approach provides new insights into the reverse engineering of physical devices.
Collapse
|
5
|
Huang G, Guo Y, Chen Y, Nie Z. Application of Machine Learning in Material Synthesis and Property Prediction. MATERIALS (BASEL, SWITZERLAND) 2023; 16:5977. [PMID: 37687675 PMCID: PMC10488794 DOI: 10.3390/ma16175977] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 07/31/2023] [Revised: 08/22/2023] [Accepted: 08/28/2023] [Indexed: 09/10/2023]
Abstract
Material innovation plays a very important role in technological progress and industrial development. Traditional experimental exploration and numerical simulation often require considerable time and resources. A new approach is urgently needed to accelerate the discovery and exploration of new materials. Machine learning can greatly reduce computational costs, shorten the development cycle, and improve computational accuracy. It has become one of the most promising research approaches in the process of novel material screening and material property prediction. In recent years, machine learning has been widely used in many fields of research, such as superconductivity, thermoelectrics, photovoltaics, catalysis, and high-entropy alloys. In this review, the basic principles of machine learning are briefly outlined. Several commonly used algorithms in machine learning models and their primary applications are then introduced. The research progress of machine learning in predicting material properties and guiding material synthesis is discussed. Finally, a future outlook on machine learning in the materials science field is presented.
Collapse
Affiliation(s)
| | | | | | - Zhengwei Nie
- School of Mechanical and Power Engineering, Nanjing Tech University, Nanjing 211816, China; (G.H.); (Y.G.); (Y.C.)
| |
Collapse
|
6
|
John-Herpin A, Tittl A, Kühner L, Richter F, Huang SH, Shvets G, Oh SH, Altug H. Metasurface-Enhanced Infrared Spectroscopy: An Abundance of Materials and Functionalities. ADVANCED MATERIALS (DEERFIELD BEACH, FLA.) 2023; 35:e2110163. [PMID: 35638248 DOI: 10.1002/adma.202110163] [Citation(s) in RCA: 7] [Impact Index Per Article: 7.0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 12/13/2021] [Revised: 04/15/2022] [Indexed: 06/15/2023]
Abstract
Infrared spectroscopy provides unique information on the composition and dynamics of biochemical systems by resolving the characteristic absorption fingerprints of their constituent molecules. Based on this inherent chemical specificity and the capability for label-free, noninvasive, and real-time detection, infrared spectroscopy approaches have unlocked a plethora of breakthrough applications for fields ranging from environmental monitoring and defense to chemical analysis and medical diagnostics. Nanophotonics has played a crucial role for pushing the sensitivity limits of traditional far-field spectroscopy by using resonant nanostructures to focus the incident light into nanoscale hot-spots of the electromagnetic field, greatly enhancing light-matter interaction. Metasurfaces composed of regular arrangements of such resonators further increase the design space for tailoring this nanoscale light control both spectrally and spatially, which has established them as an invaluable toolkit for surface-enhanced spectroscopy. Starting from the fundamental concepts of metasurface-enhanced infrared spectroscopy, a broad palette of resonator geometries, materials, and arrangements for realizing highly sensitive metadevices is showcased, with a special focus on emerging systems such as phononic and 2D van der Waals materials, and integration with waveguides for lab-on-a-chip devices. Furthermore, advanced sensor functionalities of metasurface-based infrared spectroscopy, including multiresonance, tunability, dielectrophoresis, live cell sensing, and machine-learning-aided analysis are highlighted.
Collapse
Affiliation(s)
- Aurelian John-Herpin
- Institute of Bioengineering, École Polytechnique Fédérale de Lausanne (EPFL), Lausanne, 1015, Switzerland
| | - Andreas Tittl
- Chair in Hybrid Nanosystems, Nanoinstitute Munich, Faculty of Physics, Ludwig-Maximilians-Universität München, 80539, Munich, Germany
| | - Lucca Kühner
- Chair in Hybrid Nanosystems, Nanoinstitute Munich, Faculty of Physics, Ludwig-Maximilians-Universität München, 80539, Munich, Germany
| | - Felix Richter
- Institute of Bioengineering, École Polytechnique Fédérale de Lausanne (EPFL), Lausanne, 1015, Switzerland
| | - Steven H Huang
- School of Applied and Engineering Physics, Cornell University, Ithaca, NY, 14853, USA
| | - Gennady Shvets
- School of Applied and Engineering Physics, Cornell University, Ithaca, NY, 14853, USA
| | - Sang-Hyun Oh
- Department of Electrical and Computer Engineering, University of Minnesota, Minneapolis, MN, 55455, USA
| | - Hatice Altug
- Institute of Bioengineering, École Polytechnique Fédérale de Lausanne (EPFL), Lausanne, 1015, Switzerland
| |
Collapse
|
7
|
Hong Y, Nicholls DP. Data-driven design of thin-film optical systems using deep active learning. OPTICS EXPRESS 2022; 30:22901-22910. [PMID: 36224980 DOI: 10.1364/oe.459295] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Received: 03/23/2022] [Accepted: 05/26/2022] [Indexed: 06/16/2023]
Abstract
A deep learning aided optimization algorithm for the design of flat thin-film multilayer optical systems is developed. The authors introduce a deep generative neural network, based on a variational autoencoder, to perform the optimization of photonic devices. This algorithm allows one to find a near-optimal solution to the inverse design problem of creating an anti-reflective grating, a fundamental problem in material science. As a proof of concept, the authors demonstrate the method's capabilities for designing an anti-reflective flat thin-film stack consisting of multiple material types. We designed and constructed a dielectric stack on silicon that exhibits an average reflection of 1.52 %, which is lower than other recently published experiments in the engineering and physics literature. In addition to its superior performance, the computational cost of our algorithm based on the deep generative model is much lower than traditional nonlinear optimization algorithms. These results demonstrate that advanced concepts in deep learning can drive the capabilities of inverse design algorithms for photonics. In addition, the authors develop an accurate regression model using deep active learning to predict the total reflectivity for a given optical system. The surrogate model of the governing partial differential equations can then be broadly used in the design of optical systems and to rapidly evaluate their behavior.
Collapse
|
8
|
Liang B, Xu D, Yu N, Xu Y, Ma X, Liu Q, Asif MS, Yan R, Liu M. Physics-Guided Neural-Network-Based Inverse Design of a Photonic -Plasmonic Nanodevice for Superfocusing. ACS APPLIED MATERIALS & INTERFACES 2022; 14:27397-27404. [PMID: 35649169 DOI: 10.1021/acsami.2c05083] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/15/2023]
Abstract
Controlling the nanoscale light-matter interaction using superfocusing hybrid photonic-plasmonic devices has attracted significant research interest in tackling existing challenges, including converting efficiencies, working bandwidths, and manufacturing complexities. With the growth in demand for efficient photonic-plasmonic input-output interfaces to improve plasmonic device performances, sophisticated designs with multiple optimization parameters are required, which comes with an unaffordable computation cost. Machine learning methods can significantly reduce the cost of computations compared to numerical simulations, but the input-output dimension mismatch remains a challenging problem. Here, we introduce a physics-guided two-stage machine learning network that uses the improved coupled-mode theory for optical waveguides to guide the learning module and improve the accuracy of predictive engines to 98.5%. A near-unity coupling efficiency with symmetry-breaking selectivity is predicted by the inverse design. By fabricating photonic-plasmonic couplers using the predicted profiles, we demonstrate that the excitation efficiency of 83% on the radially polarized surface plasmon mode can be achieved, which paves the way for super-resolution optical imaging.
Collapse
Affiliation(s)
- Boqun Liang
- Materials Science and Engineering program, University of California─Riverside, Riverside, California 92521, United States
| | - Da Xu
- Department of Electrical and Computer Engineering, University of California─Riverside, Riverside, California 92521, United States
| | - Ning Yu
- Department of Chemical and Environmental Engineering, University of California─Riverside, Riverside, California 92521, United States
| | - Yaodong Xu
- Materials Science and Engineering program, University of California─Riverside, Riverside, California 92521, United States
| | - Xuezhi Ma
- Department of Electrical and Computer Engineering, University of California─Riverside, Riverside, California 92521, United States
| | - Qiushi Liu
- Department of Electrical and Computer Engineering, University of California─Riverside, Riverside, California 92521, United States
| | - M Salman Asif
- Department of Electrical and Computer Engineering, University of California─Riverside, Riverside, California 92521, United States
- Department of Computer Science and Engineering, University of California─Riverside, Riverside, California 92521, United States
| | - Ruoxue Yan
- Materials Science and Engineering program, University of California─Riverside, Riverside, California 92521, United States
- Department of Chemical and Environmental Engineering, University of California─Riverside, Riverside, California 92521, United States
| | - Ming Liu
- Materials Science and Engineering program, University of California─Riverside, Riverside, California 92521, United States
- Department of Electrical and Computer Engineering, University of California─Riverside, Riverside, California 92521, United States
| |
Collapse
|
9
|
Ren S, Mahendra A, Khatib O, Deng Y, Padilla WJ, Malof JM. Inverse deep learning methods and benchmarks for artificial electromagnetic material design. NANOSCALE 2022; 14:3958-3969. [PMID: 35226023 DOI: 10.1039/d1nr08346e] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/14/2023]
Abstract
In this work we investigate the use of deep inverse models (DIMs) for designing artificial electromagnetic materials (AEMs) - such as metamaterials, photonic crystals, and plasmonics - to achieve some desired scattering properties (e.g., transmission or reflection spectrum). DIMs are deep neural networks (i.e., deep learning models) that are specially-designed to solve ill-posed inverse problems. There has recently been tremendous growth in the use of DIMs for solving AEM design problems however there has been little comparison of these approaches to examine their absolute and relative performance capabilities. In this work we compare eight state-of-the-art DIMs on three unique AEM design problems, including two models that are novel to the AEM community. Our results indicate that DIMs can rapidly produce accurate designs to achieve a custom desired scattering on all three problems. Although no single model always performs best, the Neural-Adjoint approach achieves the best overall performance across all problem settings. As a final contribution we show that not all AEM design problems are ill-posed, and in such cases a conventional deep neural network can perform better than DIMs. We recommend that a deep neural network is always employed as a simple baseline approach when addressing AEM design problems. We publish python code for our AEM simulators and our DIMs to enable easy replication of our results, and benchmarking of new DIMs by the AEM community.
Collapse
Affiliation(s)
- Simiao Ren
- Department of Electrical and Computer Engineering, Duke University, Box 90291, Durham, NC 27708, USA.
| | - Ashwin Mahendra
- Department of Electrical and Computer Engineering, Duke University, Box 90291, Durham, NC 27708, USA.
| | - Omar Khatib
- Department of Electrical and Computer Engineering, Duke University, Box 90291, Durham, NC 27708, USA.
| | - Yang Deng
- Department of Electrical and Computer Engineering, Duke University, Box 90291, Durham, NC 27708, USA.
| | - Willie J Padilla
- Department of Electrical and Computer Engineering, Duke University, Box 90291, Durham, NC 27708, USA.
| | - Jordan M Malof
- Department of Electrical and Computer Engineering, Duke University, Box 90291, Durham, NC 27708, USA.
| |
Collapse
|
10
|
Kadulkar S, Sherman ZM, Ganesan V, Truskett TM. Machine Learning-Assisted Design of Material Properties. Annu Rev Chem Biomol Eng 2022; 13:235-254. [PMID: 35300515 DOI: 10.1146/annurev-chembioeng-092220-024340] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/09/2022]
Abstract
Designing functional materials requires a deep search through multidimensional spaces for system parameters that yield desirable material properties. For cases where conventional parameter sweeps or trial-and-error sampling are impractical, inverse methods that frame design as a constrained optimization problem present an attractive alternative. However, even efficient algorithms require time- and resource-intensive characterization of material properties many times during optimization, imposing a design bottleneck. Approaches that incorporate machine learning can help address this limitation and accelerate the discovery of materials with targeted properties. In this article, we review how to leverage machine learning to reduce dimensionality in order to effectively explore design space, accelerate property evaluation, and generate unconventional material structures with optimal properties. We also discuss promising future directions, including integration of machine learning into multiple stages of a design algorithm and interpretation of machine learning models to understand how design parameters relate to material properties. Expected final online publication date for the Annual Review of Chemical and Biomolecular Engineering, Volume 13 is October 2022. Please see http://www.annualreviews.org/page/journal/pubdates for revised estimates.
Collapse
Affiliation(s)
- Sanket Kadulkar
- McKetta Department of Chemical Engineering, University of Texas at Austin, Austin, Texas, USA;
| | - Zachary M Sherman
- McKetta Department of Chemical Engineering, University of Texas at Austin, Austin, Texas, USA;
| | - Venkat Ganesan
- McKetta Department of Chemical Engineering, University of Texas at Austin, Austin, Texas, USA;
| | - Thomas M Truskett
- McKetta Department of Chemical Engineering, University of Texas at Austin, Austin, Texas, USA; .,Department of Physics, University of Texas at Austin, Austin, Texas, USA
| |
Collapse
|
11
|
Wan C, Woolf D, Hessel CM, Salman J, Xiao Y, Yao C, Wright A, Hensley JM, Kats MA. Switchable Induced-Transmission Filters Enabled by Vanadium Dioxide. NANO LETTERS 2022; 22:6-13. [PMID: 34958595 DOI: 10.1021/acs.nanolett.1c02296] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/14/2023]
Abstract
An induced-transmission filter (ITF) uses an ultrathin metallic layer positioned at an electric-field node within a dielectric thin-film bandpass filter to select one transmission band while suppressing other bands that would have been present without the metal layer. We introduce a switchable mid-infrared ITF where the metal can be "switched on and off", enabling the modulation of the filter response from a single band to multiband. The switching is enabled by the reversible insulator-to-metal phase transition of a subwavelength film of vanadium dioxide (VO2). Our work generalizes the ITF─a niche type of bandpass filter─into a new class of tunable devices. Furthermore, our fabrication process─which begins with thin-film VO2 on a suspended membrane─enables the integration of VO2 into any thin-film assembly that is compatible with physical vapor deposition processes and is thus a new platform for realizing tunable thin-film filters.
Collapse
Affiliation(s)
- Chenghao Wan
- Department of Electrical and Engineering, University of Wisconsin─Madison, Madison, Wisconsin 53706, United States
- Department of Materials Science and Engineering, University of Wisconsin─Madison, Madison, Wisconsin 53706, United States
| | - David Woolf
- Physical Sciences, Inc., Andover, Massachusetts 01810, United States
| | - Colin M Hessel
- Physical Sciences, Inc., Andover, Massachusetts 01810, United States
| | - Jad Salman
- Department of Electrical and Engineering, University of Wisconsin─Madison, Madison, Wisconsin 53706, United States
| | - Yuzhe Xiao
- Department of Electrical and Engineering, University of Wisconsin─Madison, Madison, Wisconsin 53706, United States
| | - Chunhui Yao
- Department of Electrical and Engineering, University of Wisconsin─Madison, Madison, Wisconsin 53706, United States
| | - Albert Wright
- Physical Sciences, Inc., Andover, Massachusetts 01810, United States
| | - Joel M Hensley
- Physical Sciences, Inc., Andover, Massachusetts 01810, United States
| | - Mikhail A Kats
- Department of Electrical and Engineering, University of Wisconsin─Madison, Madison, Wisconsin 53706, United States
- Department of Materials Science and Engineering, University of Wisconsin─Madison, Madison, Wisconsin 53706, United States
- Department of Physics, University of Wisconsin─Madison, Madison, Wisconsin 53706, United States
| |
Collapse
|
12
|
Unni R, Yao K, Han X, Zhou M, Zheng Y. A mixture-density-based tandem optimization network for on-demand inverse design of thin-film high reflectors. NANOPHOTONICS 2021; 10:4057-4065. [PMID: 36425324 PMCID: PMC9651023 DOI: 10.1515/nanoph-2021-0392] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 07/20/2021] [Accepted: 09/27/2021] [Indexed: 06/04/2023]
Abstract
Deep learning (DL) has emerged as a promising tool for photonic inverse design. Nevertheless, despite the initial success in retrieving spectra of modest complexity with nearly instantaneous readout, DL-assisted design methods often underperform in accuracy compared with advanced optimization techniques and have not proven competitive in handling spectra of practical usefulness. Here, we introduce a tandem optimization model that combines a mixture density network (MDN) and a fully connected (FC) network to inversely design practical thin-film high reflectors. The multimodal nature of the MDN gives access to infinite candidate designs described by probability distributions, which are iteratively sampled and evaluated by the FC network to allow for rapid optimization. We show that the proposed model can retrieve the reflectance spectra of 20-layer thin-film structures. More interestingly, it reproduces with high precision the periodic structures of high reflectors derived from physical principles, even though no such information is included in the training data. Improved designs with extended high-reflectance zones are also demonstrated. Our approach combines the high-efficiency advantage of DL with the optimization-enabled performance improvement, enabling efficient and on-demand inverse design for practical applications.
Collapse
Affiliation(s)
- Rohit Unni
- Walker Department of Mechanical Engineering, The University of Texas at Austin, Austin, TX78712, USA
- Texas Materials Institute, The University of Texas at Austin, Austin, TX78712, USA
| | - Kan Yao
- Walker Department of Mechanical Engineering, The University of Texas at Austin, Austin, TX78712, USA
- Texas Materials Institute, The University of Texas at Austin, Austin, TX78712, USA
| | - Xizewen Han
- Department of Statistics and Data Science, The University of Texas at Austin, Austin, TX78712, USA
| | - Mingyuan Zhou
- Department of Statistics and Data Science, The University of Texas at Austin, Austin, TX78712, USA
- McCombs School of Business, The University of Texas at Austin, Austin, TX78712, USA
| | - Yuebing Zheng
- Walker Department of Mechanical Engineering, The University of Texas at Austin, Austin, TX78712, USA
- Texas Materials Institute, The University of Texas at Austin, Austin, TX78712, USA
| |
Collapse
|
13
|
Kim KT, Lee DR. Probabilistic parameter estimation using a Gaussian mixture density network: application to X-ray reflectivity data curve fitting. J Appl Crystallogr 2021. [DOI: 10.1107/s1600576721009043] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/10/2022] Open
Abstract
X-ray reflectivity (XRR) is widely used for thin-film structure analysis, and XRR data analysis involves minimizing the difference between experimental data and an XRR curve calculated from model parameters describing the thin-film structure. This analysis takes a certain amount of time because it involves many unavoidable iterations. However, the recently introduced artificial neural network (ANN) method can dramatically reduce the analysis time in the case of repeated analyses of similar samples. Here, the analysis of XRR data using a mixture density network (MDN) is demonstrated, which enables probabilistic prediction while maintaining the advantages of an ANN. First, under the assumption of a unimodal probability distribution of the output parameter, the trained MDN can estimate the best-fit parameter and, at the same time, estimate the confidence interval (CI) corresponding to the error bar of the best-fit parameter. The CI obtained in this manner is similar to that obtained using the Neumann process, a well known statistical method. Next, the MDN method provides several possible solutions for each parameter in the case of a multimodal distribution of the output parameters. An unsupervised machine learning method is used to cluster possible parameter sets in order of probability. Determining the true value by examining the candidates of the parameter sets obtained in this manner can help solve the inherent inverse problem associated with scattering data.
Collapse
|
14
|
Du Q, Zhang Q, Liu G. Deep learning: an efficient method for plasmonic design of geometric nanoparticles. NANOTECHNOLOGY 2021; 32:505607. [PMID: 34530417 DOI: 10.1088/1361-6528/ac2769] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Received: 07/27/2021] [Accepted: 09/16/2021] [Indexed: 06/13/2023]
Abstract
Plasmons of noble metal nanoparticles have played an important role in energy transfer research, biomedical sensing, drug preparation and photocatalysis in recent years. The scattering spectra of nanoparticles are dramatically affected by numerous complex parameters, such as morphology, material, and volumes, making the parameters design a necessary step before the experiment. However, the plasmonic design is limited by several difficulties, such as the high degree of freedom, expensive trial and error costs. Herein, a plasmonic design method based on dual strategy deep learning is proposed, which can provide the design proposals according to the required spectrum. To make the model closer to the real experimental situation, the boundary element method was used to build a scattering spectra dataset of geometric nanoparticles (>1200 000 samples). Driven by the above data, the artificial intelligence (AI) model learns the relationship between spectral features and design parameters. Then, the performance statistics of the model were implemented from multiple dimensions, and a high design precision of over 90% was achieved in testing cases (testing samples >120 000). Moreover, to verify the realizability of the proposed model, the scattering spectra of nanoparticles designed by AI were constructed using a dark-field microscope system. The experimental results showed that the deviation between the target and the actual spectra was very small and within the acceptable range. This proves the realizability of the AI model proposed in this paper, and sheds light on the application of AI in plasmonic design.
Collapse
Affiliation(s)
- Qian Du
- College of Electronic Information and Optical Engineering, Nankai University, Tianjin 300350, People's Republic of China
- Tianjin Key Laboratory of Optoelectronic Sensor and Sensing Network Technology, Nankai University, Tianjin 300350, People's Republic of China
| | - Quan Zhang
- College of Electronic Information and Optical Engineering, Nankai University, Tianjin 300350, People's Republic of China
- Tianjin Key Laboratory of Optoelectronic Sensor and Sensing Network Technology, Nankai University, Tianjin 300350, People's Republic of China
| | - Guohua Liu
- College of Electronic Information and Optical Engineering, Nankai University, Tianjin 300350, People's Republic of China
- Tianjin Key Laboratory of Optoelectronic Sensor and Sensing Network Technology, Nankai University, Tianjin 300350, People's Republic of China
| |
Collapse
|
15
|
Fouchier M, Zerrad M, Lequime M, Amra C. Design of multilayer optical thin-films based on light scattering properties and using deep neural networks. OPTICS EXPRESS 2021; 29:32627-32638. [PMID: 34615328 DOI: 10.1364/oe.437789] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Received: 07/14/2021] [Accepted: 08/31/2021] [Indexed: 06/13/2023]
Abstract
Despite limiting the performance of multilayer optical thin-films, light scattering properties are not as yet controllable by current design methods. These methods usually consider only specular properties: transmittance and reflectance. Among other techniques, design of thin-film components assisted by deep neural networks have seen growing interest over the last few years. This paper presents an implementation of a deep neural network model for light scattering design and proposes an optimization process for complex multilayer thin-film components to comply with expectations on both specular and scattering spectral responses.
Collapse
|
16
|
Qiu C, Wu X, Luo Z, Yang H, He G, Huang B. Nanophotonic inverse design with deep neural networks based on knowledge transfer using imbalanced datasets. OPTICS EXPRESS 2021; 29:28406-28415. [PMID: 34614972 DOI: 10.1364/oe.435427] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Received: 06/30/2021] [Accepted: 08/03/2021] [Indexed: 06/13/2023]
Abstract
Deep neural networks (DNNs) have been used as a new method for nanophotonic inverse design. However, DNNs need a huge dataset to train if we need to select materials from the material library for the inverse design. This puts the DNN method into a dilemma of poor performance with a small training dataset or loss of the advantage of short design time, for collecting a large amount of data is time consuming. In this work, we propose a multi-scenario training method for the DNN model using imbalanced datasets. The imbalanced datasets used by our method is nearly four times smaller compared with other training methods. We believe that as the material library increases, the advantages of the imbalanced datasets will become more obvious. Using the high-precision predictive DNN model obtained by this new method, different multilayer nanoparticles and multilayer nanofilms have been designed with a hybrid optimization algorithm combining genetic algorithm and gradient descent optimization algorithm. The advantage of our method is that it can freely select discrete materials from the material library and simultaneously find the inverse design of discrete material type and continuous structural parameters of the nanophotonic devices.
Collapse
|
17
|
Fang J, Swain A, Unni R, Zheng Y. Decoding Optical Data with Machine Learning. LASER & PHOTONICS REVIEWS 2021; 15:2000422. [PMID: 34539925 PMCID: PMC8443240 DOI: 10.1002/lpor.202000422] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 09/25/2020] [Indexed: 05/24/2023]
Abstract
Optical spectroscopy and imaging techniques play important roles in many fields such as disease diagnosis, biological study, information technology, optical science, and materials science. Over the past decade, machine learning (ML) has proved promising in decoding complex data, enabling rapid and accurate analysis of optical spectra and images. This review aims to shed light on various ML algorithms for optical data analysis with a focus on their applications in a wide range of fields. The goal of this work is to sketch the validity of ML-based optical data decoding. The review concludes with an outlook on unaddressed problems and opportunities in this emerging subject that interfaces optics, data science and ML.
Collapse
Affiliation(s)
- Jie Fang
- Walker Department of Mechanical Engineering and Texas Materials Institute, The University of Texas at Austin, Austin, TX 78712, USA
| | - Anand Swain
- Walker Department of Mechanical Engineering and Texas Materials Institute, The University of Texas at Austin, Austin, TX 78712, USA
| | - Rohit Unni
- Walker Department of Mechanical Engineering and Texas Materials Institute, The University of Texas at Austin, Austin, TX 78712, USA
| | - Yuebing Zheng
- Walker Department of Mechanical Engineering and Texas Materials Institute, The University of Texas at Austin, Austin, TX 78712, USA
| |
Collapse
|