Experiment-based deep learning approach for power allocation with a programmable metasurface

Metasurfaces designed with deep learning approaches have emerged as efficient tools for manipulating electromagnetic waves to achieve beam steering and power allocation objectives. However, the effects of complex environmental factors like obstacle blocking and other unavoidable scattering need to be sufficiently considered for practical applications. In this work, we employ an experiment-based deep learning approach for programmable metasurface design to control powers delivered to specific locations generally with obstacle blocking. Without prior physical knowledge of the complex system, large sets of experimental data can be efficiently collected with a programmable metasurface to train a deep neural network (DNN). The experimental data can inherently incorporate complex factors that are difficult to include if only simulation data are used for training. Moreover, the DNN can be updated by collecting new experimental data on-site to adapt to changes in the environment. Our proposed experiment-based DNN demonstrates significant potential for intelligent wireless communication, imaging, sensing, and quiet-zone control for practical applications.

[1]  Ray C. C. Cheung,et al.  Generation of time-varying orbital angular momentum beams with space-time-coding digital metasurface , 2023, Advanced Photonics.

[2]  Bo Xiong,et al.  Software-defined nanophotonic devices and systems empowered by machine learning , 2023, Progress in Quantum Electronics.

[3]  Huangzhe Lu,et al.  Soft Actor–Critic-Driven Adaptive Focusing under Obstacles , 2023, Materials.

[4]  C. Chan,et al.  Sideband-free space–time-coding metasurface antennas , 2022, Nature Electronics.

[5]  Lei Zhang,et al.  Artificial Neural Network for Direction‐of‐Arrival Estimation and Secure Wireless Communications Via Space‐Time‐Coding Digital Metasurfaces , 2022, Advanced Optical Materials.

[6]  Scott A. Longwell,et al.  Metasurface optofluidics for dynamic control of light fields , 2022, Nature Nanotechnology.

[7]  Guomin Yang,et al.  Recent Progress in Reconfigurable and Intelligent Metasurfaces: A Comprehensive Review of Tuning Mechanisms, Hardware Designs, and Applications , 2022, Advanced Science.

[8]  Guomin Yang,et al.  Recent Progress in Reconfigurable and Intelligent Metasurfaces: A Comprehensive Review of Tuning Mechanisms, Hardware Designs, and Applications (Adv. Sci. 33/2022) , 2022, Advanced science.

[9]  Tianhang Chen,et al.  Programmable metasurface RCS prediction under obstacles based on DNN , 2022, Frontiers in Materials.

[10]  J. Rho,et al.  Reconfigurable Reflective Metasurface Reinforced by Optimizing Mutual Coupling Based on a Deep Neural Network , 2022, Photonics and Nanostructures - Fundamentals and Applications.

[11]  I. Kaminer,et al.  Homeostatic neuro-metasurfaces for dynamic wireless channel management , 2022, Science advances.

[12]  Ming Zheng Chen,et al.  Asynchronous Space‐Time‐Coding Digital Metasurface , 2022, Advanced science.

[13]  Erping Li,et al.  Heterogeneous Transfer‐Learning‐Enabled Diverse Metasurface Design , 2022, Advanced Optical Materials.

[14]  Juejun Hu,et al.  Active metasurfaces: lighting the path to commercial success , 2022, 2205.14193.

[15]  Hua Cheng,et al.  Deep‐Learning Enabled Multicolor Meta‐Holography , 2022, Advanced Optical Materials.

[16]  B. Alpert,et al.  Physics-assisted Generative Adversarial Network for X-Ray Tomography , 2022, Optics express.

[17]  Bo Xiong,et al.  Pushing the Limits of Functionality‐Multiplexing Capability in Metasurface Design Based on Statistical Machine Learning , 2022, Advanced materials.

[18]  Hail Lin,et al.  Machine-learning-assisted inverse design of scattering enhanced metasurface. , 2022, Optics express.

[19]  Yu Sun,et al.  Recovery of continuous 3D refractive index maps from discrete intensity-only measurements using neural fields , 2021, Nature Machine Intelligence.

[20]  Yongmin Liu,et al.  Electrically Driven Tunable Broadband Polarization States via Active Metasurfaces Based on Joule‐Heat‐Induced Phase Transition of Vanadium Dioxide , 2021, Laser & Photonics Reviews.

[21]  Yong Li,et al.  Deep learning enables accurate sound redistribution via nonlocal metasurfaces , 2021, Physical Review Applied.

[22]  Jiafu Wang,et al.  Phase-to-pattern inverse design paradigm for fast realization of functional metasurfaces via transfer learning , 2021, Nature Communications.

[23]  Bo Xiong,et al.  Realizing Colorful Holographic Mimicry by Metasurfaces , 2021, Advanced materials.

[24]  Ming Zheng Chen,et al.  A wireless communication scheme based on space- and frequency-division multiplexing using digital metasurfaces , 2021 .

[25]  Kaushik Sengupta,et al.  A high-speed programmable and scalable terahertz holographic metasurface based on tiled CMOS chips , 2020, Nature Electronics.

[26]  Peter R. Wiecha,et al.  Deep learning in nano-photonics: inverse design and beyond , 2020, Photonics Research.

[27]  Shumin Xiao,et al.  Reprogrammable meta-hologram for optical encryption , 2020, Nature Communications.

[28]  Wei Ma,et al.  Deep learning for the design of photonic structures , 2020, Nature Photonics.

[29]  Hualiang Zhang,et al.  Electrically reconfigurable non-volatile metasurface using low-loss optical phase-change material , 2020, Nature Nanotechnology.

[30]  E. N. Economou,et al.  Toward Intelligent Metasurfaces: The Progress from Globally Tunable Metasurfaces to Software‐Defined Metasurfaces with an Embedded Network of Controllers , 2020, Advanced Optical Materials.

[31]  N. Al-Dhahir,et al.  Reconfigurable Intelligent Surfaces: Principles and Opportunities , 2020, IEEE Communications Surveys & Tutorials.

[32]  Vladimir M. Shalaev,et al.  Machine learning–assisted global optimization of photonic devices , 2020, Frontiers in Optics and Photonics.

[33]  Jiaqi Jiang,et al.  Deep neural networks for the evaluation and design of photonic devices , 2020, Nature Reviews Materials.

[34]  Anjie Cao,et al.  High‐Efficiency Transmissive Programmable Metasurface for Multimode OAM Generation , 2020, Advanced Optical Materials.

[35]  Tie Jun Cui,et al.  High‐Efficiency Synthesizer for Spatial Waves Based on Space‐Time‐Coding Digital Metasurface , 2020, Laser & Photonics Reviews.

[36]  Harry A. Atwater,et al.  Electro-Optically Tunable Multifunctional Metasurfaces. , 2020, ACS nano.

[37]  Lian Shen,et al.  Deep-learning-enabled self-adaptive microwave cloak without human intervention , 2020 .

[38]  Bowen Zheng,et al.  A Deep Learning Approach for Objective-Driven All-Dielectric Metasurface Design , 2019, ACS Photonics.

[39]  J. Rho,et al.  Biomimetic Ultra-Broadband Perfect Absorbers Optimised with Reinforcement Learning , 2019, Physical chemistry chemical physics : PCCP.

[40]  A. Kildishev,et al.  Machine-learning-assisted metasurface design for high-efficiency thermal emitter optimization , 2019, Applied Physics Reviews.

[41]  A. Ozcan,et al.  Design of task-specific optical systems using broadband diffractive neural networks , 2019, Light: Science & Applications.

[42]  Qian Ma,et al.  Intelligent metasurface imager and recognizer , 2019, Light: Science & Applications.

[43]  T. Cui,et al.  Breaking Reciprocity with Space‐Time‐Coding Digital Metasurfaces , 2019, Advanced materials.

[44]  Lei Zhou,et al.  Tunable/Reconfigurable Metasurfaces: Physics and Applications , 2019, Research.

[45]  Chau Yuen,et al.  Indoor Signal Focusing with Deep Learning Designed Reconfigurable Intelligent Surfaces , 2019, 2019 IEEE 20th International Workshop on Signal Processing Advances in Wireless Communications (SPAWC).

[46]  Vladimir M. Shalaev,et al.  Spatiotemporal light control with active metasurfaces , 2019, Science.

[47]  Jianxun Su,et al.  Ultrawideband Radar Cross-Section Reduction by a Metasurface Based on Defect Lattices and Multiwave Destructive Interference , 2019, Physical Review Applied.

[48]  Yongfeng Li,et al.  Deep Learning: A Rapid and Efficient Route to Automatic Metasurface Design , 2019, Advanced science.

[49]  Trevon Badloe,et al.  Optimisation of colour generation from dielectric nanostructures using reinforcement learning. , 2019, Optics express.

[50]  Feng Cheng,et al.  Probabilistic Representation and Inverse Design of Metamaterials Based on a Deep Generative Model with Semi‐Supervised Learning Strategy , 2019, Advanced materials.

[51]  Qiang Cheng,et al.  Space-time-coding digital metasurfaces , 2018, Nature Communications.

[52]  Chau Yuen,et al.  Reconfigurable Intelligent Surfaces for Energy Efficiency in Wireless Communication , 2018, IEEE Transactions on Wireless Communications.

[53]  Michael Mrejen,et al.  Plasmonic nanostructure design and characterization via Deep Learning , 2018, Light: Science & Applications.

[54]  Yongmin Liu,et al.  Deep-Learning-Enabled On-Demand Design of Chiral Metamaterials. , 2018, ACS nano.

[55]  W. Cai,et al.  A Generative Model for Inverse Design of Metamaterials , 2018, Nano letters.

[56]  Zongfu Yu,et al.  Training Deep Neural Networks for the Inverse Design of Nanophotonic Structures , 2017, 2019 Conference on Lasers and Electro-Optics (CLEO).

[57]  Shuang Zhang,et al.  Electromagnetic reprogrammable coding-metasurface holograms , 2017, Nature Communications.

[58]  Bo O. Zhu,et al.  A Reconfigurable Active Huygens' Metalens , 2017, Advanced materials.

[59]  Maokun Li,et al.  A programmable metasurface with dynamic polarization, scattering and focusing control , 2016, Scientific Reports.

[60]  J. Teng,et al.  Optically reconfigurable metasurfaces and photonic devices based on phase change materials , 2015, Nature Photonics.

[61]  Alexander Y. Piggott,et al.  Inverse design and demonstration of a compact and broadband on-chip wavelength demultiplexer , 2015, Nature Photonics.

[62]  Qiang Cheng,et al.  Coding metamaterials, digital metamaterials and programmable metamaterials , 2014, Light: Science & Applications.

[63]  O. Sigmund,et al.  Topology optimization for nano‐photonics , 2011 .

[64]  J. Pendry,et al.  Three-Dimensional Invisibility Cloak at Optical Wavelengths , 2010, Science.

[65]  E. Ulin-Avila,et al.  Three-dimensional optical metamaterial with a negative refractive index , 2008, Nature.

[66]  Willie J Padilla,et al.  Perfect metamaterial absorber. , 2008, Physical review letters.

[67]  David R. Smith,et al.  Metamaterial Electromagnetic Cloak at Microwave Frequencies , 2006, Science.

[68]  Willie J Padilla,et al.  Active terahertz metamaterial devices , 2006, Nature.

[69]  N. Fang,et al.  Sub–Diffraction-Limited Optical Imaging with a Silver Superlens , 2005, Science.

[70]  R. Shelby,et al.  Experimental Verification of a Negative Index of Refraction , 2001, Science.

[71]  K. Mahmoud,et al.  Design of Intelligence Reflector Metasurface Using Deep Learning Neural Network for 6G Adaptive Beamforming , 2022, IEEE Access.

[72]  Sylvain Blaize,et al.  Engineering colors in all-dielectric metasurfaces: metamodeling approach , 2019 .

[73]  Willie J. Padilla,et al.  Dynamic electromagnetic metamaterials , 2015 .