Convolutional Neural Network to Predict the Penetration Coefficient of Metamaterials Based on Their Structure and Composition
Article Sidebar
Main Article Content
Abstract
The work is devoted to the development of a technique for predicting the coefficient passage of metamaterials based on topological structure and chemical composition with the use of machine learning techniques, namely artificial neural networks using convolution. In modern scientific and technical research, the methods of machine learning, namely: convolutional neural networks, occupy the most rapidly researched method in the design tasks of metamaterials and their properties. The advantage of this technique is the ease of implementation, the availability of data for this approach, the speed of calculations compared to the exact methods of predicting properties and topological structure based on physical laws. Of course, artificial neural networks are a rather complex process that has its own drawbacks – the need for a large amount of data, the relative complexity of optimization, and the complexity of problem formulation. With the development of machine learning technologies, these disadvantages are more and more eliminated, and therefore their use becomes more accessible. A large amount of information about metamaterials from relevant sources was used, namely the topology, chemical composition and measurement conditions of metamaterials. Software environments were used for writing digital code and building 3D objects of metamaterials with defined properties. An algorithm for predicting the transmission coefficient based on the structure, chemical composition of metamaterials based on a convolutional neural network using experimental data of laboratory metamaterials has been developed. An algorithm for saving information about the chemical composition of metamaterials has been developed. It is shown that using information about the electromagnetic properties of chemical elements, it is possible to predict the transmission coefficient of metamaterials. The process of presenting the coefficient of passage of metamaterials in a form convenient for training a convolutional neural network is described. Two methods were used to compare the effectiveness of both methods. It is shown that the method of representing experimental characteristics in the form of polynomial coefficients is faster, but not suitable for solving problems of predicting the characteristics of metamaterials. Data augmentation is shown to be the most effective method for improving forecasting results. Nevertheless, performance improvement methods based on architecture changes and hyperparameter changes should be continually evaluated and used whenever possible.
Article Details
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
References
N. I. Zheludev, “The Road Ahead for Metamaterials,” Science (1979), vol. 328, no. 5978, pp. 582–583, Apr. 2010, DOI: https://doi.org/10.1126/science.1186756
D. Ozevin and S. Tol, “Role of acoustic metamaterials and phononic crystals in sensing and damage detection in solids,” in The Rise of Smart Cities, Elsevier, 2022, pp. 115–137, DOI: https://doi.org/10.1016/B978-0-12-817784-6.00014-X
E. Semouchkina, “Periodic arrays of dielectric resonators as metamaterials and photonic crystals,” in Dielectric Metamaterials and Metasurfaces in Transformation Optics and Photonics, Elsevier, 2022, pp. 1–20, DOI: https://doi.org/10.1016/B978-0-12-820596-9.00008-X
M. Maasch, Tunable Microwave Metamaterial Structures, 1st ed. Springer, 2016, ISBN: 978-3319802909
A. Sprafke and J. Schilling, “Non-resonant dielectric metamaterials,” in Dielectric Metamaterials, Elsevier, 2020, pp. 249–288, DOI: https://doi.org/10.1016/B978-0-08-102403-4.00014-1
T. Gric and O. Hess, “Electromagnetics of Metamaterials,” in Phenomena of Optical Metamaterials, Elsevier, 2019, pp. 41–73, DOI: https://doi.org/10.1016/B978-0-12-813896-0.00002-X
J. Sun and N. M. Litchinitser, “Metamaterials,” in Fundamentals and Applications of Nanophotonics, Elsevier, 2016, pp. 253–307, DOI: https://doi.org/10.1016/B978-1-78242-464-2.00009-9
I. Goodfellow, Y. Bengio, and A. Courville, Deep Learning. The MIT Press, 2016, ISBN: 9780262035613
Y. Levine, N. Wies, O. Sharir, N. Cohen, and A. Shashua, “Tensors for deep learning theory,” in Tensors for Data Processing, Elsevier, 2022, pp. 215–248, DOI: https://doi.org/10.1016/B978-0-12-824447-0.00013-3
K. Santosh, N. Das, and S. Ghosh, “Deep learning models,” in Deep Learning Models for Medical Imaging, Elsevier, 2022, pp. 65–97, DOI: https://doi.org/10.1016/B978-0-12-824447-0.00013-3
V. Sze, Y.-H. Chen, T.-J. Yang, and J. Emer, “Efficient Processing of Deep Neural Networks: A Tutorial and Survey,” Mar. 2017, ArXiV: https://arxiv.org/abs/1703.09039
F. Ding, Z. Wang, S. He, V. M. Shalaev, and A. v. Kildishev, “Broadband High-Efficiency Half-Wave Plate: A Supercell-Based Plasmonic Metasurface Approach,” ACS Nano, vol. 9, no. 4, pp. 4111–4119, Apr. 2015, DOI: https://doi.org/10.1021/acsnano.5b00218
C. Huang, “Efficient and broadband polarization conversion with the coupled metasurfaces,” Opt Express, vol. 23, no. 25, p. 32015, Dec. 2015, DOI: https://doi.org/10.1364/OE.23.032015
A. Shaltout, J. Liu, A. Kildishev, and V. Shalaev, “Photonic spin Hall effect in gap–plasmon metasurfaces for on-chip chiroptical spectroscopy,” Optica, vol. 2, no. 10, p. 860, Oct. 2015, DOI: https://doi.org/10.1364/OPTICA.2.000860
N. K. Grady et al., “Terahertz Metamaterials for Linear Polarization Conversion and Anomalous Refraction,” Science (1979), vol. 340, no. 6138, pp. 1304–1307, Jun. 2013, DOI: https://doi.org/10.1126/science.1235399
L. Cong, Y. K. Srivastava, and R. Singh, “Inter and intra-metamolecular interaction enabled broadband high-efficiency polarization control in metasurfaces,” Appl Phys Lett, vol. 108, no. 1, p. 011110, Jan. 2016, DOI: https://doi.org/10.1063/1.4939564
P. Wang et al., “3D shape segmentation via shape fully convolutional networks,” Comput Graph, vol. 70, pp. 128–139, Feb. 2018, DOI: https://doi.org/10.1016/j.cag.2017.07.030
Y. Liang, F. He, X. Zeng, and B. Yu, “Feature-preserved convolutional neural network for 3D mesh recognition,” Appl Soft Comput, vol. 128, p. 109500, Oct. 2022, DOI: https://doi.org/10.1016/j.asoc.2022.109500
J. Raitoharju, “Convolutional neural networks,” in Deep Learning for Robot Perception and Cognition, Elsevier, 2022, pp. 35–69, DOI: https://doi.org/10.1016/B978-0-32-385787-1.00008-7
Sigaki HYD, Lenzi EK, Zola RS, Perc M, Ribeiro HV. Learning physical properties of liquid crystals with deep convolutional neural networks. Sci Rep. 2020 May 6;10(1):7664. DOI: https://doi.org/10.1038/s41598-020-63662-9
Xie, T., & Grossman, J. C, “Crystal graph convolutional neural networks for an accurate and interpretable prediction of material properties”, Physical review letters, 120(14), 145301, 2018, DOI: https://doi.org/10.1103/PhysRevLett.120.145301
Abueidda, DW, Almasri, M, Ammourah, R, Ravaioli, U, Jasiuk, “Prediction and optimization of mechanical properties of composites using convolutional neural networks”, IM & Sobh, NA 2019, Composite Structures, vol. 227, 111264. DOI: https://doi.org/10.1016/j.compstruct.2019.111264
Cecen, A., Dai, H., Yabansu, Y. C., Kalidindi, S. R., and Song, L., “Material structure-property linkages using three-dimensional convolutional neural networks”, Acta Materialia, vol. 146, pp. 76–84, 2018, DOI: https://doi.org/10.1016/j.actamat.2017.11.053
Chengping Rao, Yang Liu, “Three-dimensional convolutional neural network (3D-CNN) for heterogeneous material homogenization”, Computational Materials Science, vol. 184, 2020, 109850, ISSN 0927-0256, DOI: https://doi.org/10.1016/j.commatsci.2020.109850
PyTorch Contributors, “CONV3D,” 2022. [Online]. Available: https://pytorch.org/docs/stable/generated/torch.nn.Conv3d.html#torch.nn.Conv3d
