Photonics Research, Volume. 9, Issue 4, B104(2021)

Real-time deep learning design tool for far-field radiation profile

Jinran Qie1, Erfan Khoram2, Dianjing Liu2, Ming Zhou2, and Li Gao3、*
Author Affiliations
  • 1Department of Electrical and Systems Engineering, Washington University, St Louis, Missouri 63130, USA
  • 2Department of Electrical and Computer Engineering, University of Wisconsin, Madison, Wisconsin 53706, USA
  • 3Key Laboratory for Organic Electronics & Information Displays (KLOEID), Institute of Advanced Materials (IAM), and School of Materials Science and Engineering, Nanjing University of Posts & Telecommunications, Nanjing 210046, China
  • show less
    Figures & Tables(3)
    Illustration of our approach and the loss curve of the neural network. (a) Sketch of a scatterer and its far-field pattern. (b) Loss curve of our neural network.
    Examples of results from our method on: (a) random structures from the test set; and (b) typical shapes with different sizes, compared to the ground truth.
    Two examples of calculating a far-field pattern using our web tool. (a), (b) Two steps of drawing the final structure, which is the one on the right side in Fig. 2(a) and the related far-field pattern after each drawing stroke. (c), (d) Corresponding to the structures in Fig. 2(b). We also provide a video to show the design process online.
    Tools

    Get Citation

    Copy Citation Text

    Jinran Qie, Erfan Khoram, Dianjing Liu, Ming Zhou, Li Gao. Real-time deep learning design tool for far-field radiation profile[J]. Photonics Research, 2021, 9(4): B104

    Download Citation

    EndNote(RIS)BibTexPlain Text
    Save article for my favorites
    Paper Information

    Special Issue: DEEP LEARNING IN PHOTONICS

    Received: Oct. 27, 2020

    Accepted: Feb. 2, 2021

    Published Online: Apr. 6, 2021

    The Author Email: Li Gao (iamlgao@njupt.edu.cn)

    DOI:10.1364/PRJ.413567

    Topics