arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2601.17554physics.ins-dethep-ex
收藏

基于机器学习的粒子流重建在CMS探测器中的全事件解释

Full event interpretation with machine-learning-based particle-flow reconstruction in the CMS detector

European Organization for Nuclear Research (CERN)(欧洲核子研究中心)

CMS Collaboration

AI总结:

基于机器学习的粒子流重建算法在CMS探测器中实现了更高效和精确的事件重建,提升了喷注能量分辨率和推理效率。

摘要:

粒子流(PF)算法通过生成完整的最终态粒子列表,对每个粒子碰撞进行全局描述,并在CMS实验中是事件重建的核心。现有的PF实现依赖于物理驱动的启发式和假设,这些可以被直接在模拟数据上训练的机器学习(ML)模型所取代,这些模型适合现代图形处理单元(GPU)。在CMS软件框架中实现了一种最先进的基于机器学习的PF(MLPF)重建算法。MLPF算法在GPU上执行可学习的全事件重建,能够跨探测器条件和碰撞能量泛化,并用单一统一模型替代多个模块化重建步骤。在模拟和数据中,与标准PF重建相比,物理性能相当,同时提高了喷注能量分辨率和推理时间。在模拟的顶夸克-反夸克事件中,对于横动量在30-100 GeV之间的喷注,喷注能量分辨率提高了10-20%。使用模拟的多喷注事件评估推理时间,在Nvidia L4 GPU上每个事件的中位数为20 ms,相比标准CMS PF重建的约110 ms。

英文摘要:

The particle-flow (PF) algorithm constructs a global description of each particle collision by producing a comprehensive list of final-state particles, and is central to event reconstruction in the CMS experiment at the CERN LHC. The existing PF implementation relies on physics-motivated heuristics and assumptions that can be replaced by machine-learning (ML) models trained directly on simulated data and naturally suited to modern graphics processing units (GPUs). A state-of-the-art ML-based PF (MLPF) reconstruction algorithm, implemented within the CMS software framework, is presented. The MLPF algorithm performs a learnable full-event reconstruction on GPUs, generalizes across detector conditions and collision energies, and replaces multiple modular reconstruction steps with a single unified model. Physics performance comparable to standard PF reconstruction is achieved in both simulation and data, with improved jet energy resolution and inference time. In simulated top quark-antiquark events under LHC Run-3 (2023$-$2024) conditions, the jet energy resolution improves by 10$-$20% for jets with transverse momentum between 30$-$100 GeV. Inference time is evaluated using simulated multijet events, with a median of 20 ms per event on an Nvidia L4 GPU, compared to approximately 110 ms for the standard CMS PF reconstruction.

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。

↑