Abstract A new method of event characterization based on Deep Learning is presented. The PointNet models can be used for fast, online event-by-event impact parameter determination at the CBM experiment. For this study, UrQMD and the CBM detector simulation are used to generate Au+Au collision events at 10 AGeV which are then used to train and evaluate PointNet based architectures. The models can be trained on features like the hit position of particles in the CBM detector planes, tracks reconstructed from the hits or combinations thereof. The Deep Learning models reconstruct impact parameters from 2-14 fm with a mean error varying from -0.33 to 0.22 fm. For impact parameters in the range of 5-14 fm, a model which uses the combination of hit and track information of particles has a relative precision of 4-9% and a mean error of -0.33 to 0.13 fm. In the same range of impact parameters, a model with only track information has a relative precision of 4-10% and a mean error of -0.18 to 0.22 fm. This new method of event-classification is shown to be more accurate and less model dependent than conventional methods and can utilize the performance boost of modern GPU processor units.

中文翻译：

---

煤层气实验中重离子碰撞的快速中心计

摘要 提出了一种基于深度学习的事件表征新方法。PointNet 模型可用于在 CBM 实验中快速、在线确定逐事件影响参数。在本研究中，UrQMD 和 CBM 探测器模拟用于生成 10 AGeV 的 Au+Au 碰撞事件，然后用于训练和评估基于 PointNet 的架构。这些模型可以根据粒子在 CBM 探测器平面中的命中位置、从命中重建的轨迹或其组合等特征进行训练。深度学习模型重建 2-14 fm 的影响参数，平均误差从 -0.33 到 0.22 fm。对于5-14 fm范围内的冲击参数，结合粒子的命中和轨迹信息的模型相对精度为4-9%，平均误差为-0.33到0.13 fm。在相同的冲击参数范围内，只有轨道信息的模型相对精度为4-10%，平均误差为-0.18至0.22 fm。与传统方法相比，这种新的事件分类方法被证明更准确，对模型的依赖性更小，并且可以利用现代 GPU 处理器单元的性能提升。