摘要
核子分离能作为核子俘获或放出反应的反应能,对反应率起主导作用,继而会直接影响相关天体核合成过程。核脊回归(Kernel Ridge Regression,KRR)方法和考虑奇偶效应的核脊回归(Kernel Ridge Regression with odd-even effects,KRRoe)方法被应用到了核子分离能的描述中。通过分析在实验已知区域的描述精度和外推性能,详细对比讨论了两个方法对双中子分离能(S_(2n))、双质子分离能(S_(2p))、单中子分离能(S_(n))和单质子分离能(S_(p))的描述情况。发现KRR方法和KRRoe方法均能改善对双核子分离能S_(2n)和S_(2p)的描述,但是只有KRRoe方法能改善对单核子分离能Sn和Sp的描述。这主要由二者的Kernel函数的差异导致。KRR方法采用了平坦的高斯Kernel函数,因此,不能准确地给出单核子分离能的奇偶振荡行为。而KRRoe方法在Kernel中引入了奇偶差异项,准确考虑了奇偶效应,因而能较好地描述单中子分离能。
[Background]Nuclear separation energies play pivotal roles in determining nuclear reaction rates and thus significantly impact astrophysical nucleosynthesis processes.The separation energies of many neutron-rich nuclei are still beyond the capacity of experimental measurements even in the foreseeable future.[Purpose]This study aims to employ two machine learning approaches to improve nuclear separation energy predictions,including double neutron(S_(2n)),double proton(S_(2p)),single neutron(S_(n)),and single proton(S_(p))separation energies.[Methods]The Kernel Ridge Regression(KRR)and Kernel Ridge Regression with odd-even effects(KRRoe)approaches were applied to predict nuclear masses.Nuclear separation energies were calculated with the KRR and KRRoe mass models.The accuracies of these two approaches in describing experimentally known separation energies were compared.In addition,the extrapolation performances of KRR and KRRoe approaches for single nucleon separation energy and double nucleon separation energy were also compared.[Results]Both KRR and KRRoe methods improve descriptions of double nucleon separation energies S_(2n)and S_(2p).However,only the KRRoe method achieves enhanced improvement for single nucleon separation energies S_(n)and S_(p),owing to its kernel function that incorporates odd-even effects,effectively capturing the staggering behavior in these energies,unlike the KRR's flat Gaussian kernel.[Conclusions]The study demonstrates the importance of incorporating odd-even effects to accurately describe single nucleon separation energies,highlighting the superiority of the KRRoe method over the standard KRR method in the predictions of single nucleon separation energies.
作者
郭粤颖
唐湘琪
刘辉鑫
吴鑫辉
GUO Yueying;TANG Xiangqi;LIU Huixin;WU Xinhui(College of Physics and Information Engineering,Fuzhou University,Fuzhou 350108,China)
出处
《核技术》
北大核心
2025年第5期22-30,共9页
Nuclear Techniques
基金
国家自然科学基金(No.12405134)资助。
关键词
核子分离能
机器学习
核脊回归
奇偶效应
Nucleon separation energy
Machine learning
Kernel ridge regression
Odd-even effect
