arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2404.02602hep-phnucl-th
收藏

高能重离子碰撞中流观测量的深度学习

Deep learning for flow observables in high energy heavy-ion collisions

H. Hirvonen, K. J. Eskola, H. Niemi

备注：
4 pages, 4 figures. Presented at the XXXth International Conference on Ultra-relativistic Nucleus-Nucleus Collisions (Quark Matter 2023), Houston, Texas, USA
阅读 PDF
arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文提出用深度卷积神经网络从初始能量密度分布预测重离子碰撞流体力学观测量，并证明其可大幅加速多粒子流关联量的贝叶斯分析。

摘要：

我们展示了如何训练深度卷积神经网络，从初始能量密度分布预测2+1维流体力学模拟结果，包括流系数、平均横动量和带电粒子多重数。我们表明，该方法提供的结果足够准确，因此可以利用神经网络可靠地估计多粒子流关联量。此外，我们训练了能够将任意模型参数作为额外输入的网络，并通过若干示例证明其准确性仍然良好。神经网络的使用可以将利用多粒子流关联量进行贝叶斯分析所需的计算时间减少多个数量级。

英文摘要：

We demonstrate how deep convolutional neural networks can be trained to predict 2+1 D hydrodynamic simulation results for flow coefficients, mean-transverse-momentum and charged particle multiplicity from the initial energy density profile. We show that this method provides results that are accurate enough, so that one can use neural networks to reliably estimate multi-particle flow correlators. Additionally, we train networks that can take any model parameter as an additional input and demonstrate with a few examples that the accuracy remains good. The usage of neural networks can reduce the computation time needed in performing Bayesian analyses with multi-particle flow correlators by many orders of magnitude.

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。

↑