ACS Publications. Most Trusted. Most Cited. Most Read
General Inverse Design of Layered Thin-Film Materials with Convolutional Neural Networks

OR SEARCH CITATIONS

My Activity
Publications

Figure 1Loading Img
Download Hi-Res ImageDownload to MS-PowerPointCite This:ACS Photonics 2021, 8, 12, 3641-3650
    Article

    General Inverse Design of Layered Thin-Film Materials with Convolutional Neural Networks
    Click to copy article linkArticle link copied!

    Other Access OptionsSupporting Information (1)

    ACS Photonics

    Cite this: ACS Photonics 2021, 8, 12, 3641–3650
    Click to copy citationCitation copied!
    https://doi.org/10.1021/acsphotonics.1c01498
    Published November 17, 2021
    Copyright © 2021 American Chemical Society
    Request reuse permissions

    Abstract

    Click to copy section linkSection link copied!
    Abstract Image

    The design of metamaterials which support unique optical responses is the basis for most thin-film nanophotonic applications. In practice, this inverse design (ID) problem can be difficult to solve systematically due to the large design parameter space associated with general multilayered systems. We apply convolutional neural networks, a subset of deep machine learning, as a tool to solve this ID problem for metamaterials composed of stacks of thin films. We demonstrate the remarkable ability of neural networks to probe the large global design space (up to 1012 possible parameter combinations) and resolve all relationships between the metamaterial structure and corresponding ellipsometric and reflectance/transmittance spectra. The applicability of the approach is further expanded to include the ID of synthetic engineered spectra in general design scenarios. Furthermore, this approach is compared with traditional optimization methods. We find an increase in the relative optimization efficiency of the networks with the increase in the total layer number, revealing the advantage of the machine learning approach in many-layered systems where traditional methods become impractical.

    Copyright © 2021 American Chemical Society

    Subjects

    what are subjects

    Keywords

    what are keywords

    Read this article

    To access this article, please review the available access options below.

    Get instant access

    Purchase Access

    Read this article for 48 hours. Check out below using your ACS ID or as a guest.

    Recommended

    Access through Your Institution

    You may have access to this article through your institution.

    Your institution does not have access to this content. Add or change your institution or let them know you’d like them to include access.

    Supporting Information

    Click to copy section linkSection link copied!

    The Supporting Information is available free of charge at https://pubs.acs.org/doi/10.1021/acsphotonics.1c01498.

    • Link to repository for source code, link to repository for CNN models, material parameters, data set analysis, MSE landscapes, solution space analysis, CNN results analysis, impact of spectral features, details of the utilized CNN models, comparison with other machine learning methods, and comparison with the needle method (PDF)

    Terms & Conditions

    Most electronic Supporting Information files are available without a subscription to ACS Web Editions. Such files may be downloaded by article for research use (if there is a public use license linked to the relevant article, that license may permit other uses). Permission may be obtained from ACS for other uses through requests via the RightsLink permission system: http://pubs.acs.org/page/copyright/permissions.html.

    Cited By

    Click to copy section linkSection link copied!
    Citation Statements
    Explore this article's citation statements on scite.ai
    powered by  Scite

    This article is cited by 39 publications.

    1. Alexa Guglielmelli, Rosalinda Mazzei, Giovanna Palermo, Liliana Valente, Caterina M. Tone, Lidietta Giorno, Giuseppe Strangi, Teresa Poerio. Development of a Photothermal Regenerative Plasmonic Platform as a Light-Controlled Interface. ACS Applied Materials & Interfaces 2024, 16 (43) , 59586-59596. https://doi.org/10.1021/acsami.4c13455
    2. Xiaogen Yuan, Zhongchao Wei, Qiongxiong Ma, Wen Ding, Jianping Guo. Multitask Learning Deep Neural Networks Enable Embedded Design of Active Metamaterials. ACS Applied Materials & Interfaces 2024, 16 (20) , 26500-26511. https://doi.org/10.1021/acsami.4c01730
    3. Jaewoong Choi, Byungju Lee. Quantitative Topic Analysis of Materials Science Literature Using Natural Language Processing. ACS Applied Materials & Interfaces 2024, 16 (2) , 1957-1968. https://doi.org/10.1021/acsami.3c12301
    4. M. R. Mahani, Yasmin Rahimof, Sten Wenzel, Igor Nechepurenko, Andreas Wicht. Data-Efficient Machine Learning Algorithms for the Design of Surface Bragg Gratings. ACS Applied Optical Materials 2023, 1 (8) , 1474-1484. https://doi.org/10.1021/acsaom.3c00198
    5. Chen Luo, Tian Sang. Strategical deep learning for customized circular dichroism through chiral quasi-bound states in the continuum. Optics & Laser Technology 2025, 184 , 112500. https://doi.org/10.1016/j.optlastec.2025.112500
    6. Huakun Xia, Shu-Lin Chen, Yuxin Wang, Yijia Zhao, Heping Jia, Rongcao Yang, Y. Jay Guo. Deep-learning-assisted intelligent design of terahertz hybrid-functional metasurfaces with freeform patterns. Optics & Laser Technology 2025, 181 , 112041. https://doi.org/10.1016/j.optlastec.2024.112041
    7. Alexa Guglielmelli, Rossella Zaffino, Giovanna Palermo, Liliana Valente, Dante Maria Aceti, Loredana Ricciardi, Arántzazu González‐Campo, Raphael Pfattner, Núria Aliaga‐Alcalde, Giuseppe Strangi. Plasmonic Coupling for High‐Sensitivity Detection of Low Molecular Weight Molecules. Small Science 2025, 5 (1) https://doi.org/10.1002/smsc.202400382
    8. Jiawei Yang, Kaiyu Cui, Yidong Huang, Wei Zhang, Xue Feng, Fang Liu. Angle‐Insensitive Spectral Imaging Based on Topology‐Optimized Plasmonic Metasurfaces. Laser & Photonics Reviews 2024, 18 (12) https://doi.org/10.1002/lpor.202400255
    9. Minghai Tang, Lei Wang, Zhiqiang Xin, Zikun Luo. High energy absorption design of porous metals using deep learning. International Journal of Mechanical Sciences 2024, 282 , 109593. https://doi.org/10.1016/j.ijmecsci.2024.109593
    10. Zhongzheng Zhang, Hongwei Li, Yabin Hu, Yongquan Liu, Yongbo Li, Bing Li. Few-sample information-enhanced inverse design framework for customizing transmission-modulated elastic metasurfaces. International Journal of Mechanical Sciences 2024, 279 , 109507. https://doi.org/10.1016/j.ijmecsci.2024.109507
    11. Barak Hadad, Omry Oren, Alon Bahabad. On the benefit of attention in inverse design of thin films filters. Machine Learning: Science and Technology 2024, 5 (3) , 035034. https://doi.org/10.1088/2632-2153/ad6832
    12. Lei Wang, Jian Dong, Wenjie Zhang, Chong Zheng, Linhua Liu. Inverse design for laser-compatible infrared camouflage metasurface enabled by physics-driven neural network and genetic algorithm. Optical Materials 2024, 153 , 115639. https://doi.org/10.1016/j.optmat.2024.115639
    13. Amir Ghasemi, Rui Fang, Dagou A. Zeze, Mehdi Keshavarz Hedayati, , , . AI-based optical materials discovery. 2024, 20. https://doi.org/10.1117/12.3017154
    14. Kandammathe Valiyaveedu Sreekanth, Sambhu Jana, Mohamed ElKabbash, Ranjan Singh, Jinghua Teng. Phase change material-based tunable Fano resonant optical coatings and their applications. Nanophotonics 2024, 13 (12) , 2075-2088. https://doi.org/10.1515/nanoph-2023-0723
    15. Qingshan Yu, Barnaby R. M. Norris, Göran Edvell, Liguo Luo, Joss Bland-Hawthorn, Sergio G. Leon-Saval. Inverse design and optimization of an aperiodic multi-notch fiber Bragg grating using neural networks. Applied Optics 2024, 63 (14) , D50. https://doi.org/10.1364/AO.514987
    16. Ivan Alonso Lujan-Cabrera, Cesar Isaza, Ely Karina Anaya-Rivera, Cristian Felipe Ramirez-Gutierrez. Inverse design of incommensurate one-dimensional porous silicon photonic crystals using 2D-convolutional mixture density neural networks. Photonics and Nanostructures - Fundamentals and Applications 2024, 59 , 101260. https://doi.org/10.1016/j.photonics.2024.101260
    17. Menglong Luo, Sang-Shin Lee. Tandem neural network-assisted inverse design of highly efficient diffractive slanted waveguide grating. Optics Express 2024, 32 (7) , 12587. https://doi.org/10.1364/OE.514502
    18. Christopher Yeung, Benjamin Pham, Zihan Zhang, Katherine T. Fountaine, Aaswath P. Raman. Hybrid supervised and reinforcement learning for the design and optimization of nanophotonic structures. Optics Express 2024, 32 (6) , 9920. https://doi.org/10.1364/OE.512159
    19. Pan Liu, Yongqiang Zhao, Ning Li, Kai Feng, Seong G. Kong, Chaolong Tang. Deep neural networks with adaptive solution space for inverse design of multilayer deep-etched grating. Optics and Lasers in Engineering 2024, 174 , 107933. https://doi.org/10.1016/j.optlaseng.2023.107933
    20. D.G. Gulevich, I.R. Nabiev, P.S. Samokhvalov. Machine learning–assisted colloidal synthesis: A review. Materials Today Chemistry 2024, 35 , 101837. https://doi.org/10.1016/j.mtchem.2023.101837
    21. Min Gao, Chaoyi Yin, Jianda Shao, Meiping Zhu. Neural network modeling and prediction of HfO 2 thin film properties tuned by thermal annealing. High Power Laser Science and Engineering 2024, 12 https://doi.org/10.1017/hpl.2024.6
    22. 葛宏义 Ge Hongyi, 补雨薇 Bu Yuwei, 蒋玉英 Jiang Yuying, 季晓迪 Ji Xiaodi, 贾柯柯 Jia Keke, 吴旭阳 Wu Xuyang, 张元 Zhang Yuan, 张玉洁 Zhang Yujie, 孙庆成 Sun Qingcheng, 王顺 Wang Shun. 人工智能在太赫兹超材料设计与优化领域的研究进展. Laser & Optoelectronics Progress 2024, 61 (23) , 2300003. https://doi.org/10.3788/LOP240937
    23. Juwon Jung, Kibaek Kim, Junho Choi, NaGyeong Kim, Won Chegal, Yong Jai Cho, Young-Joo Kim. Geometric analysis algorithm based on a neural network with localized simulation data for nano-grating structure using Mueller matrix spectroscopic ellipsometry. Optics Express 2023, 31 (26) , 44364. https://doi.org/10.1364/OE.507102
    24. Ross Glyn MacDonald, Alex Yakovlev, Victor Pacheco-Peña. Time derivatives via interconnected waveguides. Scientific Reports 2023, 13 (1) https://doi.org/10.1038/s41598-023-40046-3
    25. Barak Hadad, Sahar Froim, Erez Yosef, Raja Giryes, Alon Bahabad. Deep learning in optics—a tutorial. Journal of Optics 2023, 25 (12) , 123501. https://doi.org/10.1088/2040-8986/ad08dc
    26. Yunyi Chen, Nan Lin, . A high efficiency metrology for asymmetric grating structure based on scalar diffraction theory and intelligence optimization. 2023, 122. https://doi.org/10.1117/12.3007646
    27. Mohammad Abu-Mualla, Jida Huang. Inverse design of 3D cellular materials with physics-guided machine learning. Materials & Design 2023, 232 , 112103. https://doi.org/10.1016/j.matdes.2023.112103
    28. Andrew Lininger, Akeshi Aththanayake, Jonathan Boyd, Omar Ali, Madhav Goel, Yangheng Jizhe, Michael Hinczewski, Giuseppe Strangi. Machine learning to optimize additive manufacturing for visible photonics. Nanophotonics 2023, 12 (14) , 2767-2778. https://doi.org/10.1515/nanoph-2022-0815
    29. Zongyong Pan, Xiaomin Pan. Deep Learning and Adjoint Method Accelerated Inverse Design in Photonics: A Review. Photonics 2023, 10 (7) , 852. https://doi.org/10.3390/photonics10070852
    30. Jining Wang, Yaohui Zhan, Wei Ma, Hongyu Zhu, Yao Li, Xiaofeng Li. Machine learning enabled rational design for dynamic thermal emitters with phase change materials. iScience 2023, 26 (6) , 106857. https://doi.org/10.1016/j.isci.2023.106857
    31. Huan Tran, Tuoc N. Vu. Machine-learning approach for discovery of conventional superconductors. Physical Review Materials 2023, 7 (5) https://doi.org/10.1103/PhysRevMaterials.7.054805
    32. Omer Yesilyurt, Samuel Peana, Vahagn Mkhitaryan, Karthik Pagadala, Vladimir M. Shalaev, Alexander V. Kildishev, Alexandra Boltasseva. Fabrication-conscious neural network based inverse design of single-material variable-index multilayer films. Nanophotonics 2023, 12 (5) , 993-1006. https://doi.org/10.1515/nanoph-2022-0537
    33. Xianghui Liu, Pan Wang, Chengyu Xiao, Liucheng Fu, Jun Xu, Di Zhang, Han Zhou, Tongxiang Fan. Compatible Stealth Metasurface for Laser and Infrared with Radiative Thermal Engineering Enabled by Machine Learning. Advanced Functional Materials 2023, 33 (11) https://doi.org/10.1002/adfm.202212068
    34. Tony Knightley, Alex Yakovlev, Victor Pacheco‐Peña. Neural Network Design of Multilayer Metamaterial for Temporal Differentiation. Advanced Optical Materials 2023, 11 (5) https://doi.org/10.1002/adom.202202351
    35. Jun Yu, Shu Zhan, Toru Kurihara. Wide-Angular Tolerance Optical Filter Design and Its Application to Green Pepper Segmentation. Sensors 2023, 23 (6) , 2981. https://doi.org/10.3390/s23062981
    36. Jaebum Noh, Trevon Badloe, Chihun Lee, Jooyeong Yun, Sunae So, Junsuk Rho. Inverse design meets nanophotonics: From computational optimization to artificial neural network. 2023, 3-32. https://doi.org/10.1016/B978-0-323-85796-3.00001-9
    37. Sarah Head, Mehdi Keshavarz Hedayati. Inverse Design of Distributed Bragg Reflectors Using Deep Learning. Applied Sciences 2022, 12 (10) , 4877. https://doi.org/10.3390/app12104877
    38. Jia Wang, Yingxue Wang, Yanan Chen. Inverse Design of Materials by Machine Learning. Materials 2022, 15 (5) , 1811. https://doi.org/10.3390/ma15051811
    39. Aybike URAL, Zeynep Hilal KİLİMCİ. The Prediction of Chiral Metamaterial Resonance using Convolutional Neural Networks and Conventional Machine Learning Algorithms. International Journal of Computational and Experimental Science and Engineering 2021, 7 (3) , 156-163. https://doi.org/10.22399/ijcesen.973726
    Download PDF
    Go to ACS Photonics
    Get e-Alerts
    Get e-Alerts

    ACS Photonics

    Cite this: ACS Photonics 2021, 8, 12, 3641–3650
    Click to copy citationCitation copied!
    https://doi.org/10.1021/acsphotonics.1c01498
    Published November 17, 2021
    Copyright © 2021 American Chemical Society
    Request reuse permissions

    Article Views

    2283

    Altmetric

    -

    Citations

    39
    Learn about these metrics

    Article Views are the COUNTER-compliant sum of full text article downloads since November 2008 (both PDF and HTML) across all institutions and individuals. These metrics are regularly updated to reflect usage leading up to the last few days.

    Citations are the number of other articles citing this article, calculated by Crossref and updated daily. Find more information about Crossref citation counts.

    The Altmetric Attention Score is a quantitative measure of the attention that a research article has received online. Clicking on the donut icon will load a page at altmetric.com with additional details about the score and the social media presence for the given article. Find more information on the Altmetric Attention Score and how the score is calculated.