Fuyuan Wu, Xiaohu Yang, Yanyun Ma, Qi Zhang, Zhe Zhang, Xiaohui Yuan, Hao Liu, Zhengdong Liu, Jiayong Zhong, Jian Zheng, Yutong Li, Jie Zhang. Machine-learning guided optimization of laser pulses for direct-drive implosions[J]. High Power Laser Science and Engineering, 2022, 10(2): 02000e12
- High Power Laser Science and Engineering
- Vol. 10, Issue 2, 02000e12 (2022)
Fig. 1. Schematic of the DCI target structure and laser pulse to be optimized in this paper.
Fig. 2. Plasma implosion diagram and laser pulses obtained by (a) manual optimization and (b) machine-learning optimization.
Fig. 3. (a) Typical laser pulses searched by the genetic algorithm and (b) the evolution of population fitness during the optimization.
Fig. 4. (a) Feature importance obtained by the random forest algorithm and (b) scatter diagram of the ion temperature and the areal density for the last two rounds of optimization.
Fig. 5. (a) Typical laser pulse power in a cone and (b) double-cone target used in the 2021 DCI summer experiments.
|
Table 1. Typical properties of manual optimization and machine-learning optimization.
|
Table 2. Comparison of the predicted and observed results in the DCI experimental campaign.
Set citation alerts for the article
Please enter your email address
© Copyright 2018-2021 | Chinese Laser Press. All Rights Reserved 沪ICP备15018463号-20