Advanced Photonics Nexus, Volume. 4, Issue 4, 046016(2025)

Active learning–augmented end-to-end modeling toward fast inverse design in chirped pulse amplification

Helin Jiang, Guoqing Pu*, Xinyi Ma, Weisheng Hu, and Lilin Yi*
Author Affiliations
  • Shanghai Jiao Tong University, School of Information Science and Electronic Engineering, State Key Laboratory of Photonics and Communications, Shanghai, China
  • show less
    Figures & Tables(10)
    Concise illustration of the CPA simulation system.
    (a) Proposed E2E model for simulating the CPA system. (b) Workflow of the active learning strategy.
    Output pulses of the E2E-AL model and SSFM-RK4. (a)–(c) Comparison of the intensity and phase in the spectral domain. (d)–(f) Comparison of the intensity and phase in the temporal domain. (g)–(i) Comparison of the intensity and phase in the temporal domain after fine-tuning compression. (j)–(l) Comparison of the intensity and phase in the spectral domain after fine-tuning compression.
    Intensity NRMSE and time consumption comparison between the SSFM-RK4 and E2E-AL model.
    Results of the active learning. The NRMSE of the E2E (red solid line) and E2E-AL (blue solid line) models under different train samples. The active learning strategy reduces the number of training samples as indicated by the yellow dashed line.
    Inverse design workflow of the CPA system.
    Inverse design comparison between the SSFM-RK4 and E2E-AL under different target pulses. (a) and (b) Single-objective inverse design of the pulse duration. (c) and (d) Multi-objective inverse design of the pulse duration and energy. (a) and (c) Temporal intensity comparison among the target pulse, the result of the SSFM-RK4 and GA, and the result of the E2E-AL and GA. (b) and (d) Error comparison between the most matching pulse of the SSFM-RK4 and GA and the E2E-AL and GA with the target pulse in each generation.
    • Table 1. Parameters of the CPA system.

      View table
      View in Article

      Table 1. Parameters of the CPA system.

      TypePropertyValue
      SystemTemporal window4 ns
      Temporal resolution20 fs
      Seed pulseCentral wavelength1030 nm
      Duration100 to 500 fs
      Energy0.5 to 1.5 nJ
      Chirped coefficients−2 to 2
      CFBGβ219.175 to 19.739  ps2
      β3−0.1565 to 0.1875  ps3
      YDF 1Core diameter6  μm
      Cladding diameter125  μm
      Length1 m
      Pump 1Gain10 to 15 dB
      YDF 2Core diameter14  μm
      Cladding diameter125  μm
      Length1 m
      Pump 2Gain10 to 14 dB
      NKT rod fiberCore diameter85  μm
      Cladding diameter260  μm
      Length0.8 m
      Pump 3Gain10 to 14 dB
      Grating pairsGrating distance0.358 m
      Grating period1/1600 mm
      Angle of incidence55.558 deg
    • Table 2. Comparison between the SSFM-RK4 and E2E-AL model.

      View table
      View in Article

      Table 2. Comparison between the SSFM-RK4 and E2E-AL model.

      SSFM-RK4SSFM-RK4SSFM-RK4E2E-AL
      Step size1 mm6 mm16 mmN/A
      Simulation timea198 s32 s13 s0.015 s
      Memoryb9509 MB4885 MB1054 MB62 MB
      Intensity NRMSEN/A0.001450.022320.00108
      Phase NRMSEN/A0.001040.120880.00199
      Energy MAPEN/A0.47%7.24%0.51%
      Duration MAPEN/A000
      Training timeN/AN/AN/A11,254 s
      Training sampleN/AN/AN/A45,000
    • Table 3. Time consumption comparison of the CPA system inverse design.a

      View table
      View in Article

      Table 3. Time consumption comparison of the CPA system inverse design.a

      E2E-AL and GASSFM-RK4 and GA
      Model time (s)0.002534.8068
      Fine-tuning compression time (s)1.31891.4543
      Total time (s)1.321536.2611
    Tools

    Get Citation

    Copy Citation Text

    Helin Jiang, Guoqing Pu, Xinyi Ma, Weisheng Hu, Lilin Yi, "Active learning–augmented end-to-end modeling toward fast inverse design in chirped pulse amplification," Adv. Photon. Nexus 4, 046016 (2025)

    Download Citation

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

    Category: Research Articles

    Received: Dec. 17, 2024

    Accepted: May. 27, 2025

    Published Online: Aug. 11, 2025

    The Author Email: Guoqing Pu (teddyghf1994@sjtu.edu.cn), Lilin Yi (lilinyi@sjtu.edu.cn)

    DOI:10.1117/1.APN.4.4.046016

    CSTR:32397.14.1.APN.4.4.046016

    Topics