CoChat
Sign Up
Cited by 32Advanced Photonic Communication SystemsNeural Networks and Reservoir ComputingMetamaterials and Metasurfaces Applications

The DOI matches its Crossref record; 2 of the 2 references it cites were found in a registry or an index.

Super-resolution diffractive neural network for all-optical direction of arrival estimation beyond diffraction limits

Open access
Gao, Sheng, Chen, Hang, Wang, Yichen, Duan, Zhengyang, Zhang, Haiou, Sun, Zhi, Shen, Yuan, Lin, Xing·2024·Light: Science & Applications
DOI 10.1038/s41377-024-01511-4PMC PMC11237115
Open this paper in CoChat — free account

Abstract

Wireless sensing of the wave propagation direction from radio sources lays the foundation for communication, radar, navigation, etc. However, the existing signal processing paradigm for the direction of arrival estimation requires the radio frequency electronic circuit to demodulate and sample the multichannel baseband signals followed by a complicated computing process, which places the fundamental limit on its sensing speed and energy efficiency. Here, we propose the super-resolution diffractive neural networks (S-DNN) to process electromagnetic (EM) waves directly for the DOA estimation at the speed of light. The multilayer meta-structures of S-DNN generate super-oscillatory angular responses in local angular regions that can perform the all-optical DOA estimation with angular resolutions beyond the diffraction limit. The spatial-temporal multiplexing of passive and reconfigurable S-DNNs is utilized to achieve high-resolution DOA estimation over a wide field of view. The S-DNN is validated for the DOA estimation of multiple radio sources over 5 GHz frequency bandwidth with estimation latency over two to four orders of magnitude lower than the state-of-the-art commercial devices in principle. The results achieve the angular resolution over an order of magnitude, experimentally demonstrated with four times, higher than diffraction-limited resolution. We also apply S-DNN's edge computing capability, assisted by reconfigurable intelligent surfaces, for extremely low-latency integrated sensing and communication with low power consumption. Our work is a significant step towards utilizing photonic computing processors to facilitate various wireless sensing and communication tasks with advantages in both computing paradigms and performance over electronic computing.

Overview

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1038/s41377-024-01511-4

Cites

2 of 2 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

  • Gao et al. designed a SIM for estimating the direction-of-arrival of multiple radio sources over a 5 GHz bandwidth, using spatial-temporal multiplexing to achieve high-resolution DOA estimation over a wide field of view.

    “Additionally, Gao et al. [75] designed a SIM for estimating the direction-ofarrival (DOA) of multiple radio sources over a 5 GHz bandwidth. Spatial-temporal multiplexing was utilized to achieve high-resolution DOA estimation over a wide field of view.”

    From Emerging Technologies in Intelligent Metasurfaces: Shaping the Future of Wireless Communications (2026) · cites this paper as [75]

    The Abstract (page not specified) states that Gao et al. used spatial-temporal multiplexing for high-resolution DOA estimation over a wide field of view and validated estimation of multiple radio sources over a 5 GHz bandwidth. However, it calls the designed system a super-resolution diffractive neural network (S-DNN), not a SIM. (LLM, conf=0.88)

    Experimental — accuracy not yet measured

  • Gao et al. [75] demonstrated that the angular resolution of the SIM can even exceed the diffraction limit.

    “They demonstrated that the angular resolution of the SIM can even exceed the diffraction limit.”

    From Emerging Technologies in Intelligent Metasurfaces: Shaping the Future of Wireless Communications (2026) · cites this paper as [75]

    The Results section reports angular resolution beyond the Rayleigh diffraction limit, including 0.4° resolution in numerical evaluations. But the device studied is a super-resolution diffractive neural network (S-DNN), not a SIM, so the claim's attribution of that result to a SIM is unsupported. The provided copy gives no page number. (LLM, conf=0.86)

    Experimental — accuracy not yet measured

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Flagged first, then by citations

Research works printed but not linked: 50

  1. Schmidt, R. Multiple emitter location and signal parameter estimation. IEEE Trans. Antennas Propag. 34, 276–280 (1986). · DOI · Paper page
  2. Tan, Z., Eldar, Y. C. & Nehorai, A. Direction of arrival estimation using co-prime arrays: a super resolution viewpoint. IEEE Trans. Signal Process. 62, 5565–5576 (2014). · DOI
  3. Huang, H. J. et al. Deep learning for super-resolution channel estimation and DOA estimation based massive MIMO system. IEEE Trans. Vehicular Technol. 67, 8549–8560 (2018). · DOI
  4. Lin, X. Artificial intelligence built on wireless signals. Nat. Electron. 5, 69–70 (2022). · DOI
  5. Dang, S. P. et al. What should 6 G be? Nat. Electron. 3, 20–29 (2020). · DOI · Paper page
  6. Bogaerts, W. et al. Programmable photonic circuits. Nature 586, 207–216 (2020). · DOI
  7. Shastri, B. J. et al. Photonics for artificial intelligence and neuromorphic computing. Nat. Photonics 15, 102–114 (2021). · DOI · Paper page
  8. Wetzstein, G. et al. Inference in artificial intelligence with deep optics and photonics. Nature 588, 39–47 (2020). · DOI
  9. Miscuglio, M. et al. Massively parallel amplitude-only Fourier neural network. Optica 7, 1812–1819 (2020). · DOI
  10. Zuo, Y. et al. All-optical neural network with nonlinear activation functions. Optica 6, 1132–1137 (2019). · DOI
  11. Feldmann, J. et al. Parallel convolutional processing using an integrated photonic tensor core. Nature 589, 52–58 (2021). · DOI · Paper page
  12. Feldmann, J. et al. All-optical spiking neurosynaptic networks with self-learning capabilities. Nature 569, 208–214 (2019). · DOI
  13. Shen, Y. C. et al. Deep learning with coherent nanophotonic circuits. Nat. Photonics 11, 441–446 (2017). · DOI · Paper page
  14. Xu, X. Y. et al. 11 TOPS photonic convolutional accelerator for optical neural networks. Nature 589, 44–51 (2021). · DOI
  15. Antonik, P. et al. Human action recognition with a large-scale brain-inspired photonic computer. Nat. Mach. Intell. 1, 530–537 (2019). · DOI
  16. Vandoorne, K. et al. Experimental demonstration of reservoir computing on a silicon photonics chip. Nat. Commun. 5, 3541 (2014). · DOI
  17. Sludds, A. et al. Delocalized photonic deep learning on the internet’s edge. Science 378, 270–276 (2022). · DOI
  18. Pai, S. et al. Experimentally realized in situ backpropagation for deep learning in photonic neural networks. Science 380, 398–404 (2023). · DOI
  19. Li, Y. H. et al. Quantitative phase imaging (QPI) through random diffusers using a diffractive optical network. Light 4, 19 (2023).
  20. Luo, Y. et al. Computational imaging without a computer: seeing through random diffusers at the speed of light. eLight 2, 4 (2022). · DOI
  21. Wu, Z. et al. Three-dimensional nanoscale reduced-angle ptycho-tomographic imaging with deep learning (RAPID). eLight 3, 7 (2023). · DOI
  22. Zhou, Z. et al. Prospects and applications of on-chip lasers. eLight 3, 1 (2023). · DOI
  23. Marpaung, D., Yao, J. P. & Capmany, J. Integrated microwave photonics. Nat. Photonics 13, 80–90 (2019). · DOI · Paper page
  24. Liu, W. L. et al. A fully reconfigurable photonic integrated signal processor. Nat. Photonics 10, 190–195 (2016). · DOI
  25. Zhang, W. P. et al. Broadband physical layer cognitive radio with an integrated photonic processor for blind source separation. Nat. Commun. 14, 1107 (2023). · DOI
  26. Gao, S., Wu, C. & Lin, X. Demixing microwave signals using system-on-chip photonic processor. Light 13, 58 (2024). · DOI
  27. Qian, C. et al. Dynamic recognition and mirage using neuro-metamaterials. Nat. Commun. 13, 2694 (2022). · DOI
  28. Gao, X. X. et al. Programmable surface plasmonic neural networks for microwave detection and processing. Nat. Electron. 6, 319–328 (2023). · DOI · Paper page
  29. Chen, M. K. et al. A meta-device for intelligent depth perception. Adv. Mater. 35, 2107465 (2023). · DOI
  30. Cui, T. J. et al. Coding metamaterials, digital metamaterials and programmable metamaterials. Light 3, e218 (2014). · DOI · Paper page
  31. Huang, C. X. et al. Polarization modulation for wireless communications based on metasurfaces. Adv. Funct. Mater. 31, 2103379 (2021). · DOI
  32. Zhang, L. et al. A wireless communication scheme based on space- and frequency-division multiplexing using digital metasurfaces. Nat. Electron. 4, 218–227 (2021). · DOI
  33. Wei, M. L. et al. Metasurface-enabled smart wireless attacks at the physical layer. Nat. Electron. 6, 610–618 (2023). · DOI
  34. Zhang, X. G. et al. An optically driven digital metasurface for programming electromagnetic functions. Nat. Electron. 3, 165–171 (2020). · DOI
  35. Wei, L. et al. Channel estimation for RIS-empowered multi-user MISO wireless communications. IEEE Trans. Commun. 69, 4144–4157 (2021). · DOI
  36. Zhu, J. A. et al. Sensing RISs: enabling dimension-independent CSI acquisition for beamforming. IEEE Trans. Inf. Theory 69, 3795–3813 (2023). · DOI
  37. Zheng, Z. Y. et al. Dual adaptive training of photonic neural networks. Nat. Mach. Intell. 5, 1119–1129, https://doi.org/10.1038/s42256-023-00723-4 (2023). · DOI
  38. Zhou, T. K. et al. Large-scale neuromorphic optoelectronic computing with a reconfigurable diffractive processing unit. Nat. Photonics 15, 367–373 (2021). · DOI
  39. Xiong, H. et al. A metamaterial energy power detector based on electromagnetic energy harvesting technology. ACS Appl. Electron. Mater. 6, 1204–1210 (2024). · DOI
  40. Li, W. H. et al. Intelligent metasurface system for automatic tracking of moving targets and wireless communications based on computer vision. Nat. Commun. 14, 989 (2023). · DOI
  41. Huang, M. et al. Machine-learning-enabled metasurface for direction of arrival estimation. Nanophotonics 11, 2001–2010 (2022). · DOI
  42. Li, L. L. et al. Intelligent metasurface imager and recognizer. Light 8, 97 (2019). · DOI
  43. Li, L. L. et al. Electromagnetic reprogrammable coding-metasurface holograms. Nat. Commun. 8, 197 (2017). · DOI
  44. Zhang, J. C. et al. A 6 G meta-device for 3D varifocal. Sci. Adv. 9, eadf8478 (2023). · DOI
  45. Chen, Y. T. et al. Photonic unsupervised learning variational autoencoder for high-throughput and low-latency image transmission. Sci. Adv. 9, eadf8437, https://doi.org/10.1126/sciadv.adf8437 (2023). · DOI
  46. Goi, E., Schoenhardt, S. & Gu, M. Direct retrieval of Zernike-based pupil functions using integrated diffractive deep neural networks. Nat. Commun. 13, 7531 (2022). · DOI
  47. Zhang, Y. N. et al. Ultra-broadband directional scattering by colloidally lithographed high-index Mie resonant oligomers and their energy-harvesting applications. ACS Appl. Mater. Interfaces 10, 16776–16782 (2018). · DOI
  48. Chen, H. et al. Diffractive deep neural networks at visible wavelengths. Engineering 7, 1483–1491 (2021). · DOI
  49. Duan, Z. Y., Chen, H. & Lin, X. Optical multi-task learning using multi-wavelength diffractive deep neural networks. Nanophotonics 12, 893–903 (2023). · DOI
  50. Zheng, H. Y. et al. Multichannel meta-imagers for accelerating machine vision. Nat. Nanotechnol. 19, 471–478 (2024). · DOI

Cited by

Sorted by citations

Metadata

Authors
Gao, S., Chen, H., Wang, Y., Duan, Z., Zhang, H., Sun, Z., Shen, Y., & Lin, X.
Affiliations
  • Tsinghua University (CN)
  • Beijing National Research Center for Information Science and Technology (CN)
Corresponding author
Lin, Xing
ORCID
Venue
Light: Science & Applications
Publisher
Springer Science and Business Media LLC
Published
2024-07-10
Volume
13
Issue
1
Pages
161-161
ISSN
2047-7538 (ISSN-L)
DOI
10.1038/s41377-024-01511-4
PMC
PMC11237115
OpenAlex
W4400503389
Cited by
32
References
2
Citations by year
2026: 8 · 2025: 21 · 2024: 3
FWCI
3.31
Type
journal article
Language
en
Open access
Licence
Locations
  • Light Science & Applications (publishedVersion, cc-by)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
Funders
National Natural Science Foundation of China (62275139)
Topics
  • Physical Sciences › Engineering › Electrical and Electronic Engineering › Advanced Photonic Communication Systems
  • Physical Sciences › Computer Science › Artificial Intelligence › Neural Networks and Reservoir Computing
  • Physical Sciences › Materials Science › Electronic, Optical and Magnetic Materials › Metamaterials and Metasurfaces Applications
Keywords
direction of arrival estimation, all-optical signal processing, superoscillations, diffraction limit, reconfigurable intelligent surface, integrated sensing and communication, optical computing, wireless sensing, edge computing, angular resolution

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review