Toward machine-learning-assisted PW-class high-repetition-rate experiments with solid targets

作者：D. Mariscal, B. Z. Djordjević, Rushil Anirudh, Jayaraman J. Thiagarajan, Elizabeth Grace, Raspberry Simpson, K. K. Swanson, Thomas Galvin, D. E. Mittelberger, John E. Heebner, Ryan D. Muir, Eric Folsom, M. P. Hill, Scott Feister, Eiichi Ito, K. Valdez-Sereno, J. J. Rocca, Jaebum Park, Shoujun Wang, R. Hollinger, R. Nedbailo, B. Sullivan, G. Zeraouli, Ankita Shukla, Pavan Turaga, A. Sarkar, Brian Van Essen, Shusen Liu, B. Spears, Peer‐Timo Bremer, T. Ma · 发表于：Physics of Plasmas · 年份：2024 · DOI：10.1063/5.0190553 · 被引用次数：11 · 研究领域：Laser-Plasma Interactions and Diagnostics、Laser Material Processing Techniques、Advanced X-ray Imaging Techniques

We present progress in utilizing a machine learning (ML) assisted optimization framework to study the trends in a parameter space defined by spectrally shaped, high-intensity, petawatt-class (8 J, 45 fs) laser pulses interacting with solid targets and give the first simulation-based overview of predicted trends. A neural network (NN) incorporating uncertainty quantification is trained to predict the number of hot electrons generated by the laser–target interaction as a function of pulse shaping parameters. The predictions of this NN serve as the basis function for a Bayesian optimization framework to navigate this space. For post-experimental evaluation, we compare two separate neural network (NN) models. One is based solely on data from experiments, and the other is trained only on ensemble particle-in-cell simulations. Reviewing the predicted and observed trends across the experiment-capable laser parameter search space, we find that both ML models predict a maximal increase in hot electron generation at a level of approximately 12%–18%; however, no statistically significant enhancement was observed in experiments. On direct comparison of the NN models, the average discrepancy is 8.5%, with a maximum of 30%. Since shot-to-shot fluctuations in experiments affect the observations, we evaluate the behavior of our optimization framework by performing virtual experiments that vary the number of repeated observations and the noise levels. Here, we discuss the implications of such...