基于深度学习的钻孔辐射压离子加速建模  

Modeling of ion accelerated by borehole radiation pressure based on deep learning

作　　者：张普渡 王伟权 李哲民 张资旋 王叶晨 周泓宇 银燕[1] Zhang Pu-Du;Wang Wei-Quan;Li Zhe-Min;Zhang Zi-Xuan;Wang Ye-Chen;Zhou Hong-Yu;Yin Yan(Department of Physics,National University of Defense Technology,Changsha 410073,China;Department of Mathematics,National University of Defense Technology,Changsha 410073,China)

机构地区：[1]国防科技大学理学院物理系,长沙410073 [2]国防科技大学理学院数学系,长沙410073

出　　处：《物理学报》2023年第18期107-117,共11页Acta Physica Sinica

基　　金：国家自然科学基金青年基金(批准号:12005298);国家自然科学基金联合项目“叶企孙”科学基金(批准号:U2241281);湖南省自然科学基金(批准号:2022JJ30656);湖南省自然科学基金青年基金(批准号:2021JJ40661);国防科技大学科研计划(批准号:ZK19-25)资助的课题。

摘　　要：超短超强激光脉冲与固体靶相互作用可通过钻孔辐射压加速机制产生百MeV量级的离子束,离子束的品质强烈依赖于激光和靶的作用参量.本文以近400组激光驱动固体靶的粒子模拟结果作为数据集,以激光强度、靶密度、靶厚和离子质量作为输入参量,基于全连接神经网络建立了一个离子峰值能量和截止能量连续映射模型.该模型用较为稀疏的参量取值获得了较大参量范围内的分析结果,大大减少了多维参量大范围扫参的计算量.基于连续映射模型的结果,得到了钻孔辐射压加速机制下离子峰值能量的修正公式和截止能量的拟合公式,可为激光离子加速的实验设计提供重要参考.Laser-driven ion acceleration has potential applications in high energy density matter,ion beam-driven fast ignition,beam target neutron source,warm dense matter heating,etc.Ultrashort relativistic laser interacting with solid target can generate ion beam with several hundreds of MeV in energy,and the quality of the ion beam depends strongly on the interaction parameters between the laser and the target.Development in deep learning can provide new method of analyzing the relationship between parameters in physics system,which can significantly reduce the computational and experimental cost.In this paper,a continuous mapping model of ion peak and cutoff energy is developed based on a fully connected neural network(FCNN).In the model,the dataset is composed of nearly 400 sets of particle simulations of laser-driven solid targets,and the input parameters are laser intensity,target density,target thickness,and ion mass.The model uses sparse parameter values to obtain the analysis results in a large range of parameters,which greatly reduces the computational amount of multi-dimensional parameters sweeping in a wide range.Based on the results of this model mapping,the correction formula for the ion peak energy is obtained.Furthermore,the ratio of ion cutoff energy to peak energy of each set of particle simulation is calculated.Repeating the same training process of ion peak energy and cutoff energy,the continuous mapping model of energy ratio is developed.According to the energy ratio model mapping results,the quantitative description of the relationship between ion cutoff energy and peak energy is realized,and the fitting formula for the cutoff energy of the hole-boring radiation pressure acceleration(HB-RPA)mechanism is obtained,which can provide an important reference for designing the laser-driven ion acceleration experiments.

关 键 词：激光离子加速 神经网络 

分 类 号：TN249[电子电信—物理电子学] TP18[自动化与计算机技术—控制理论与控制工程]