发表机构
Massachusetts Institute of Technology（麻省理工学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对稀有核素实验中的离子束输运难题，提出一种结合离散时间生存分析与条件归一化流的可微概率代理模型，实现毫秒级预测、电压优化与束流性质推断。
AI 中文摘要
具有极端质子-中子比的放射性原子核为核结构、基本对称性、天体物理过程以及医学等应用提供了独特的探针。然而，其短半衰期和低产率意味着实验必须处理少量目标离子，且常处于超过信号六个数量级的污染物背景之中。因此，通过多级装置高效地分离、输运并输送这些离子是一项核心挑战。我们提出了一种在粒子损耗主导区域中用于离子束输运的可微概率代理模型。该模型通过结合离散时间生存分析与条件归一化流，联合捕获离子沿束线的存活概率以及存活粒子的演化相空间分布。应用于一条高维静电束线时，所得似然函数能够实现对运行电压的基于梯度的优化，以及从稀疏探测器观测中推断束流性质。一旦训练完成，该代理模型可提供毫秒级的可微预测，将具有硬损耗的粒子跟踪模拟转化为可用于实验设计、束线优化以及未来稀有核实验数字孪生的推理就绪模型。
英文摘要
Radioactive nuclei with extreme proton-to-neutron ratios provide unique probes of nuclear structure, fundamental symmetries, astrophysical processes, and applications such as medicine. However, their short half-lives and low production rates mean that experiments must work with few desired ions, often amid contaminant backgrounds exceeding the signal by six orders of magnitude. Efficiently isolating, transporting, and delivering these ions through multi-stage apparatus is therefore a central challenge. We introduce a differentiable probabilistic surrogate for ion-beam transport in regimes dominated by particle loss. The model jointly captures the survival probability of ions along the beamline and the evolving phase-space distribution of the surviving particles by combining discrete-time survival analysis with conditional normalizing flows. Applied to a high-dimensional electrostatic beamline, the resulting likelihood enables gradient-based optimization of operating voltages and inference of beam properties from sparse detector observations. Once trained, the surrogate provides millisecond-scale differentiable predictions, transforming particle-tracking simulations with hard losses into an inference-ready model for experimental design, beamline optimization, and future digital twins of experiments with rare nuclei.
