arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2606.06210physics.plasm-ph
收藏

用于激光离子加速中跃迁映射的质子谱预测代理模型

A Surrogate Model for Proton Spectrum Prediction to Map Transitions in Laser-Ion Acceleration

Key Laboratory of Beam Technology of the Ministry of Education, and School of Physics and Astronomy, Beijing Normal University(教育部束流技术重点实验室,北京师范大学物理与天文学院);Xinjiang Key Laboratory of Solid State Physics and Devices, School of Physics Science and Technology, Xinjiang University(新疆固态物理与器件重点实验室,新疆大学物理科学与技术学院);School of Systems Science, Beijing Normal University(北京师范大学系统科学学院)

Chengqi-Zhang, Yang He, Mamat Ali Bake, Xilin-Wang, Bai-Song Xie

AI总结:

提出一种物理引导的解耦双分支代理模型,通过β-VAE与多层感知机结合,高精度预测激光驱动离子加速中的连续质子能谱,并量化不确定性,成功复现TNSA到RIT/BOA的跃迁特征。

摘要:

我们提出了一种物理引导的解耦双分支代理模型,用于预测激光驱动离子加速中的连续质子能谱。该框架将用于光谱特征提取的β-VAE与用于标量边界强制的并行多层感知机相结合,在最大截止能量上实现了R²=0.94的预测精度,总粒子通量上R²=0.94,整个2000-bin能量分布的中位每样本光谱R²=0.985(在log₁₀空间中)。该模型通过深度集成引入不确定性量化,作为定量概率诊断工具,校准误差低于6.2%。在一维纵向框架内,该代理模型复现了与靶法向鞘层加速(TNSA)到相对论诱导透明(RIT)和爆发后燃器(BOA)机制的体积加热动力学跃迁一致的光谱特征,并通过一维粒子模拟的动力学诊断进行了验证。该方法为未来的多保真度优化建立了计算高效的基线,并为高重复率激光设施中的闭环参数控制提供了引擎。

英文摘要:

We present a physics-guided, decoupled dual-branch surrogate model to predict continuous proton energy spectra from laser-driven ion acceleration. Integrating a $β$-VAE for spectral feature extraction with a parallel multi-layer perceptron for scalar boundary enforcement, the framework achieves a predictive accuracy of $R^2 = 0.94$ for the maximum cutoff energy and $R^2 = 0.94$ for the total particle flux, with a median per-sample spectral $R^2 = 0.985$ (in $\log_{10}$ space) across the full 2000-bin energy distribution. The model incorporates uncertainty quantification via deep ensembles, serving as a quantitative probabilistic diagnostic tool with calibration errors below 6.2\%. Within the 1D longitudinal framework, the surrogate reproduces spectral signatures consistent with the transition from Target Normal Sheath Acceleration (TNSA) to the volumetric heating dynamics of Relativistically Induced Transparency (RIT) and Breakout Afterburner (BOA) regimes, as validated against kinetic diagnostics from 1D particle-in-cell simulations. This approach establishes a computationally efficient baseline for future multi-fidelity optimization and provides an engine for closed-loop parameter control in high-repetition-rate laser facilities.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑