Machine learning transforms the inference of the nuclear equation of state
Machine learning transforms the inference of the nuclear equation of state
复制标题
DOI：
10.1007/s11467-023-1313-3
复制
发表时间：
2023-05
影响因子：
7.5
通讯作者：
Yongjia Wang;Qingfeng Li
中科院分区：
文献类型：
--
作者：
Yongjia Wang;Qingfeng Li
我们对致密核物质性质的了解通常是通过核实验、天体物理观测和核理论计算间接获得的。推进我们对核状态方程（EOS，这是核物理学中最重要的性质之一，也是核心兴趣所在）的理解依赖于从实验和计算中产生的各种数据。我们回顾了机器学习如何彻底改变我们从这些数据中提取EOS的方式，并总结了使用机器学习带来的挑战和机遇。
Our knowledge of the properties of dense nuclear matter is usually obtained indirectly via nuclear experiments, astrophysical observations, and nuclear theory calculations. Advancing our understanding of the nuclear equation of state (EOS, which is one of the most important properties and of central interest in nuclear physics) has relied on various data produced from experiments and calculations. We review how machine learning is revolutionizing the way we extract EOS from these data, and summarize the challenges and opportunities that come with the use of machine learning.