• High Power Laser and Particle Beams
  • Vol. 36, Issue 12, 122004 (2024)
Zhiyang Xia1, Yuanyuan Kuang1,2, Yan Lu1,*, and Ming Yang1,3,*
Author Affiliations
  • 1School of Physics and Optoelectronic Engineering, Anhui University, Hefei 230601, China
  • 2School of Electronic and Information Engineering, Anhui University, Hefei 230601, China
  • 3Institute of Artificial Intelligence, Hefei Comprehensive National Science Center, Hefei 230088, China
  • show less
    DOI: 10.11884/HPLPB202436.240015 Cite this Article
    Zhiyang Xia, Yuanyuan Kuang, Yan Lu, Ming Yang. High-resolution reconstruction of the ablative RT instability flow field via convolutional neural networks[J]. High Power Laser and Particle Beams, 2024, 36(12): 122004 Copy Citation Text show less
    Schematic diagram of ordinary CNN structure
    Fig. 1. Schematic diagram of ordinary CNN structure
    Schematic diagram of the structure of a multi-time-path CNN
    Fig. 2. Schematic diagram of the structure of a multi-time-path CNN
    Error maps of two convolutional neural network models
    Fig. 3. Error maps of two convolutional neural network models
    Comparison of reconstructed results with average pooling (r=4)
    Fig. 4. Comparison of reconstructed results with average pooling (r=4)
    Comparison of reconstructed results with maximum pooling (r=4)
    Fig. 5. Comparison of reconstructed results with maximum pooling (r=4)
    Comparison of the high-resolution reconstructed density data (weak nonlinear stage with ablation, disturbance wavelength=12 μm)
    Fig. 6. Comparison of the high-resolution reconstructed density data (weak nonlinear stage with ablation, disturbance wavelength=12 μm)
    Comparison of the high-resolution reconstructed density data (classical linear stage, disturbance wavelength=12 μm)
    Fig. 7. Comparison of the high-resolution reconstructed density data (classical linear stage, disturbance wavelength=12 μm)
    Comparison of the high-resolution reconstructed density data (nonlinear stage with ablation, disturbance wavelength=12 μm)
    Fig. 8. Comparison of the high-resolution reconstructed density data (nonlinear stage with ablation, disturbance wavelength=12 μm)
    Comparison of the high-resolution reconstructed density data (weak nonlinear stage with ablation, disturbance wavelength=30 μm)
    Fig. 9. Comparison of the high-resolution reconstructed density data (weak nonlinear stage with ablation, disturbance wavelength=30 μm)
    Zhiyang Xia, Yuanyuan Kuang, Yan Lu, Ming Yang. High-resolution reconstruction of the ablative RT instability flow field via convolutional neural networks[J]. High Power Laser and Particle Beams, 2024, 36(12): 122004
    Download Citation