High Power Laser and Particle Beams, Volume. 36, Issue 7, 071002(2024)

Research progress in deep learning for wavefront reconstruction and wavefront prediction

Congpan Qiu... Guodong Liu*, Dayong Zhang and Liusen Hu |Show fewer author(s)
Author Affiliations
  • Institute of Fluid Physics, CAEP, Mianyang 621900, China
  • show less
    Figures & Tables(12)
    An example of the wavefront validation with three different reconstruction methods: LSF, SVD, and ANN[9]
    Comparison of outputs of ISNet, optimized least squares (OLS), and Southwell algorithms at three levels of turbulence[11]
    Illustration of convolutional neural network architectures[12]
    Architecture of the neural network and process of model training and testing[13]
    Modified U-net architecture[17]
    Percentage of cases with residual RMS WFE below 1/10 of the Marechal criterion when using random starting points and the CNN’s predictions[18]
    CNN architectures[24]
    Sketch map of the feature-based phase retrieval wavefront sensing approach using machine learning[25]
    Data flow of the training and estimation processes[27]
    Comparison of the four models’ simulation results under strong turbulence and weak turbulence[37]
    Architecture for the wavefront prediction network[10]
    • Table 1. Summary of the accuracies (RMSEs) of the estimated Zernike coefficients in the experiments[23]

      View table
      View in Article

      Table 1. Summary of the accuracies (RMSEs) of the estimated Zernike coefficients in the experiments[23]

      Zernike coefficient
      in-focusover exposuredefocusscatter
      point source0.142±0.0320.036±0.0130.040±0.0160.057±0.018
      extended sources0.288±0.0240.214±0.0510.099±0.0640.195±0.064
    Tools

    Get Citation

    Copy Citation Text

    Congpan Qiu, Guodong Liu, Dayong Zhang, Liusen Hu. Research progress in deep learning for wavefront reconstruction and wavefront prediction[J]. High Power Laser and Particle Beams, 2024, 36(7): 071002

    Download Citation

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

    Category:

    Received: Dec. 5, 2023

    Accepted: Jan. 31, 2024

    Published Online: Jun. 21, 2024

    The Author Email: Liu Guodong (guodliu@126.com)

    DOI:10.11884/HPLPB202436.230430

    Topics