Deep Learning: A Rapid and Efficient Route to Automatic Metasurface Design

Advanced Science - Tập 6 Số 12 - 2019
Tianshuo Qiu1, Xin Shi2, Jiafu Wang1, Yongfeng Li1, Shaobo Qu1, Qiang Cheng3, Tie Jun Cui3, Sai Sui1
1Department of Basic Sciences, Air Force Engineering University, Xi'an, 710051, China
2School of Computer Science, Xi'an Polytechnic University, Xi'an 710048, China
3State Key Laboratory of Millimeter Waves, Southeast University, Nanjing 210096, China

Tóm tắt

AbstractMetasurfaces provide unprecedented routes to manipulations on electromagnetic waves, which can realize many exotic functionalities. Despite the rapid development of metasurfaces in recent years, the design process of metasurface is still time‐consuming and computational resource‐consuming. Moreover, it is quite complicated for layman users to design metasurfaces as plenty of specialized knowledge is required. In this work, a metasurface design method named REACTIVE is proposed on the basis of deep learning, as deep learning method has shown its natural advantages and superiorities in mining undefined rules automatically in many fields. REACTIVE is capable of calculating metasurface structure directly through a given design target; meanwhile, it also shows the advantage in making the design process automatic, more efficient, less time‐consuming, and less computational resource‐consuming. Besides, it asks for less professional knowledge, so that engineers are required only to pay attention to the design target. Herein, a triple‐band absorber is designed using the REACTIVE method, where a deep learning model computes the metasurface structure automatically through inputting the desired absorption rate. The whole design process is achieved 200 times faster than the conventional one, which convincingly demonstrates the superiority of this design method. REACTIVE is an effective design tool for designers, especially for laymen users and engineers.

Từ khóa


Tài liệu tham khảo

10.1109/MAP.2012.6230714

10.1126/science.1253213

10.1126/science.1232009

10.1126/science.1210713

10.1002/adma.201401484

Liu S., 2016, Adv. Sci., 3, 10

10.1002/adom.201700773

10.1002/adom.201700541

10.1126/sciadv.1701477

10.1002/adom.201300384

10.1002/adma.201503281

10.1021/acsphotonics.6b00392

Ran Y. Z., 2018, Opt. Express, 427, 101

Roy T., 2018, Appl. Phys. Lett., 3, 021302

10.1364/OE.22.025931

10.1109/TAP.2017.2702712

10.1038/s41377-018-0092-z

Li A. B., 2018, IEEE Trans. Microw. Theory, 7, 90

10.1021/acsphotonics.6b00653

10.1038/nature16961

10.1038/nature24270

10.1016/j.csbj.2014.11.005

10.1038/ncomms12474

10.1145/3065386

10.1109/TPAMI.2016.2599174

10.1016/j.rser.2013.03.004

10.1073/pnas.1218772110

10.1038/nature14539

10.1016/j.inffus.2017.10.006

10.1109/TAP.2016.2634281

10.1109/TAP.2016.2536175

10.1126/science.1127647

10.1126/science.290.5500.2323

10.1109/TNNLS.2016.2551724

10.1109/TPAMI.2017.2665545

10.1109/TASLP.2014.2339736

10.1109/TASSP.1980.1163420

10.1109/TASLP.2014.2364452

Liu W. B., 2017, Neurocomputing, 234, 17

Buhlmann P., 2011, J. R. Stat. Soc. B, 73, 277

10.1109/TIP.2017.2654163

10.1109/TNNLS.2012.2197412

G. E.Hinton N.Srivastava A.Krizhevsky I.Sutskever R. R.Salakhutdinov Improving neural networks by preventing co‐adaptation of feature detectors https://arxiv.org/abs/1207.0580v1(accessed: July2012).

10.1002/cem.873

10.1023/A:1010933404324

10.1080/00401706.2000.10485983

10.1109/TNNLS.2017.2673241

10.1063/1.4955412

Thông tin
Thông tin xuất bản

Advanced Science

Tập 6 Số 12

Thông tin tác giả