An artificial neural network potential for uranium metal at low pressures

doi:10.1088/1674-1056/acd8a4

中国物理B ›› 2023, Vol. 32 ›› Issue (9): 98401-098401.doi: 10.1088/1674-1056/acd8a4

An artificial neural network potential for uranium metal at low pressures

Maosheng Hao(郝茂生) and Pengfei Guan(管鹏飞)^†

Beijing Computational Science Research Center, Beijing 100193, China

收稿日期:2023-03-27 修回日期:2023-05-22 接受日期:2023-05-25 发布日期:2023-09-01
通讯作者: Pengfei Guan E-mail:pguan@csrc.ac.cn
基金资助:
We acknowledge the computational support from Beijing Computational Science Research Center (CSRC). Project supported by the National Natural Science Foundation of China (Grant Nos. 52161160330 and U2230402).

An artificial neural network potential for uranium metal at low pressures

Maosheng Hao(郝茂生) and Pengfei Guan(管鹏飞)^†

Beijing Computational Science Research Center, Beijing 100193, China

Received:2023-03-27 Revised:2023-05-22 Accepted:2023-05-25 Published:2023-09-01
Contact: Pengfei Guan E-mail:pguan@csrc.ac.cn
Supported by:
We acknowledge the computational support from Beijing Computational Science Research Center (CSRC). Project supported by the National Natural Science Foundation of China (Grant Nos. 52161160330 and U2230402).

摘要/Abstract

摘要： Based on machine learning, the high-dimensional fitting of potential energy surfaces under the framework of first principles provides density-functional accuracy of atomic interaction potential for high-precision and large-scale simulation of alloy materials. In this paper, we obtained the high-dimensional neural network (NN) potential function of uranium metal by training a large amount of first-principles calculated data. The lattice constants of uranium metal with different crystal structures, the elastic constants, and the anisotropy of lattice expansion of alpha-uranium obtained based on this potential function are highly consistent with first-principles calculation or experimental data. In addition, the calculated formation energy of vacancies in alpha- and beta-uranium also matches the first-principles calculation. The calculated site of the most stable self-interstitial and its formation energy is in good agreement with the findings from density functional theory (DFT) calculations. These results show that our potential function can be used for further large-scale molecular dynamics simulation studies of uranium metal at low pressures, and provides the basis for further construction of potential model suitable for a wide range of pressures.

关键词: machine learning potential, uranium metal, first-principles calculation

Abstract: Based on machine learning, the high-dimensional fitting of potential energy surfaces under the framework of first principles provides density-functional accuracy of atomic interaction potential for high-precision and large-scale simulation of alloy materials. In this paper, we obtained the high-dimensional neural network (NN) potential function of uranium metal by training a large amount of first-principles calculated data. The lattice constants of uranium metal with different crystal structures, the elastic constants, and the anisotropy of lattice expansion of alpha-uranium obtained based on this potential function are highly consistent with first-principles calculation or experimental data. In addition, the calculated formation energy of vacancies in alpha- and beta-uranium also matches the first-principles calculation. The calculated site of the most stable self-interstitial and its formation energy is in good agreement with the findings from density functional theory (DFT) calculations. These results show that our potential function can be used for further large-scale molecular dynamics simulation studies of uranium metal at low pressures, and provides the basis for further construction of potential model suitable for a wide range of pressures.

Key words: machine learning potential, uranium metal, first-principles calculation

中图分类号: (Neural networks)

84.35.+i

34.20.Cf (Interatomic potentials and forces) 71.20.Gj (Other metals and alloys)

Maosheng Hao(郝茂生) and Pengfei Guan(管鹏飞). An artificial neural network potential for uranium metal at low pressures[J]. 中国物理B, 2023, 32(9): 98401-098401.

Maosheng Hao(郝茂生) and Pengfei Guan(管鹏飞). An artificial neural network potential for uranium metal at low pressures[J]. Chin. Phys. B, 2023, 32(9): 98401-098401.

参考文献

[1] Smith J L and Kmetko E A 1983 J. Less-Common Met. 90 83
[2] Lander G H, Fisher E S and Bader S D 1994 Adv. Phys. 43 1
[3] Zhang L, Han J, Wang H, Car R and Weinan E 2018 Phys. Rev. Lett. 120 143001
[4] Li Y, Shan T R, Liang T, Sinnott S B and Phillpot S R 2012 J. Phys.: Condens. Matter 24 235403
[5] Pascuet M I, Bonny G and Fernández J R 2012 J. Nucl. Mater. 424 158
[6] Fernández J R and Pascuet M I 2014 Model. Simul. Mater. Sci. Eng. 22 055019
[7] Blank T B, Brown S D, Calhoun A W and Doren D J 1995 J. Chem. Phys. 103 4129
[8] Behler J and Parrinello M 2007 Phys. Rev. Lett. 98 146401
[9] Bartók A P, Payne M C, Kondor R and Csányi G 2010 Phys. Rev. Lett. 104 136403
[10] Rupp M, Tkatchenko A, Müller K R and Von Lilienfeld O A 2012 Phys. Rev. Lett. 108 058301
[11] Thompson A P, Swiler L P, Trott C R, Foiles S M and Tucker G J 2015 J. Comput. Phys. 285 316
[12] Pinheiro M, Ge F, Ferré N, Dral P O and Barbatti M 2021 Chem. Sci. 12 14396
[13] Su R, Yu J, Guan P and Wang W 2022 arXiv: 2211.03350v1 [cond-mat.mtrl-sci]
[14] Behler J 2015 Int. J. Quantum Chem. 115 1032
[15] Zhu C, Byrd R H, Lu P and Nocedal J 1997 ACM Trans. Math. Softw. 23 550
[16] Deringer V L, Pickard C J and Csányi G 2018 Phys. Rev. Lett. 120 156001
[17] Kresse G and Furthmüller J 1996 Phys. Rev. B 54 11169
[18] Blöchl P E 1994 Phys. Rev. B 50 17953
[19] Perdew J P, Burke K and Ernzerhof M 1996 Phys. Rev. Lett. 77 3865
[20] Thompson A P, Aktulga H M, Berger R, Bolintineanu D S, Brown W M, Crozier P S, in 't Veld P J, Kohlmeyer A, Moore S G, Nguyen T D, Shan R, Stevens M J, Tranchida J, Trott C and Plimpton S J 2022 Comput. Phys. Commun. 271 108171
[21] Pickard C J and Needs R J 2011 J. Phys.: Condens. Matter 23 053201
[22] Imbalzano G, Anelli A, Giofré D, Klees S, Behler J and Ceriotti M 2018 J. Chem. Phys. 148 241730
[23] Zhang L, Lin D Y, Wang H, Car R and E W 2019 Phys. Rev. Mater. 3 023804
[24] Söderlind P 1998 Adv. Phys. 47 959
[25] Wang V, Xu N, Liu J C, Tang G and Geng W T 2021 Comput. Phys. Commun. 267 108033
[26] Barrett C S, Mueller M H and Hitterman R L 1963 Phys. Rev. 129 625
[27] Lloyd L T and Barrett C S 1966 J. Nucl. Mater. 18 55
[28] Chiswik H H, Dwight A E, Lloyd L T, Nevitt M V and Zegler S T 1958 Proceedings of the 2nd United Nation International Conference on the Peaceful Uses of Atomic Energy, September 1-13, 1958, Geneva, Switzerland, p. 394
[29] Huang G Y and Wirth B D 2012 J. Phys.: Condens. Matter 24 415404
[30] Huang G Y and Wirth B D 2011 J. Phys.: Condens. Matter 23 205402
[31] Kruglov I A, Yanilkin A, Oganov A R and Korotaev P 2019 Phys. Rev. B 100 174104
[32] Smirnova D E, Starikov S V and Stegailov V V 2012 J. Phys.: Condens. Matter 24 015702
[33] Taylor C D 2008 Phys. Rev. B 77 094119
[34] Wilson A S and Rundle R E 1949 Acta Crystallogr. 2 126
[35] Li J H, Ren Q B, Lu C H, Lu L, Dai Y and Liu B X 2012 J. Alloys Compd. 516 139
[36] Taylor C D 2009 Phys. Rev. B 80 024104
[37] Fisher E S and McSkimin H J 1961 Phys. Rev. 124 67
[38] Yoo C S, Cynn H and Söderlind P 1998 Phys. Rev. B 57 10359
[39] Söderlind P 2002 Phys. Rev. B 66 085113
[40] Beeler B, Good B, Rashkeev S, Deo C, Baskes M and Okuniewski M 2010 J. Phys.: Condens. Matter 22 505703
[41] Lund K R, Lynn K G, Weber M H and Okuniewski M A 2013 J. Phys.: Conf. Ser. 443 012021
[42] Matter H, Winter J and Triftshauser W 1980 J. Nucl. Mater. 88 273

An artificial neural network potential for uranium metal at low pressures

An artificial neural network potential for uranium metal at low pressures

RichHTML

PDF (PC)

赞

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

Metrics

本文评价

推荐阅读 0

[1]	Yue-Tong Han(韩曰通), Yu-Xian Yang(杨宇贤), Ping Li(李萍), and Chang-Wen Zhang(张昌文). Design of sign-reversible Berry phase effect in 2D magneto-valley material[J]. 中国物理B, 2023, 32(9): 97101-097101.
[2]	Yu Dong(董煜), Zhi-Gang Shao(邵志刚), Cang-Long Wang(王苍龙), and Lei Yang(杨磊). Modulation of CO adsorption on 4,12,2-graphyne by Fe atom doping and applied electric field[J]. 中国物理B, 2023, 32(8): 87101-087101.
[3]	Xiaofan Yu(于小凡), Yangwu Tong(童洋武), and Yong Yang(杨勇). Quantum tunneling in the surface diffusion of single hydrogen atoms on Cu(001)[J]. 中国物理B, 2023, 32(8): 86801-086801.
[4]	Qianqian Wang(王倩倩), Jianzhou Zhao(赵建洲), Weikang Wu(吴维康), Yinning Zhou(周胤宁), Qile Li, Mark T. Edmonds, and Shengyuan A. Yang(杨声远). Magnetic and electronic properties of bulk and two-dimensional FeBi₂Te₄: A first-principles study[J]. 中国物理B, 2023, 32(8): 87506-087506.
[5]	Jing-Xuan Wang(王靖轩), Bao-Zhen Sun(孙宝珍), Mei Li(李梅), Mu-Sheng Wu(吴木生), and Bo Xu(徐波). Structural, electronic, and Li-ion mobility properties of garnet-type Li₇La₃Zr₂O₁₂ surface: An insight from first-principles calculations[J]. 中国物理B, 2023, 32(6): 68201-068201.
[6]	Zhanjun Qiu(邱占均), Yanxiao Hu(胡晏箫), Ding Li(李顶), Tao Hu(胡涛), Hong Xiao(肖红),Chunbao Feng(冯春宝), and Dengfeng Li(李登峰). Thermal transport properties of two-dimensional boron dichalcogenides from a first-principles and machine learning approach[J]. 中国物理B, 2023, 32(5): 54402-054402.
[7]	Li-Man Xiao(肖丽蔓), Huan-Cheng Yang(杨焕成), and Zhong-Yi Lu(卢仲毅). Prediction of LiCrTe₂ monolayer as a half-metallic ferromagnet with a high Curie temperature[J]. 中国物理B, 2023, 32(5): 57505-057505.
[8]	Yilin Zhang(张轶霖), Huimin Mu(穆慧敏), Yuxin Cai(蔡雨欣), Xiaoyu Wang(王啸宇), Kun Zhou(周琨), Fuyu Tian(田伏钰), Yuhao Fu(付钰豪), and Lijun Zhang(张立军). Evaluating thermal expansion in fluorides and oxides: Machine learning predictions with connectivity descriptors[J]. 中国物理B, 2023, 32(5): 56302-056302.
[9]	Ao Chen(陈奥), Hua Tong(童话), Cheng-Wei Wu(吴成伟), Guofeng Xie(谢国锋), Zhong-Xiang Xie(谢忠祥), Chang-Qing Xiang(向长青), and Wu-Xing Zhou(周五星). Stress effect on lattice thermal conductivity of anode material NiNb₂O₆ for lithium-ion batteries[J]. 中国物理B, 2023, 32(5): 58201-058201.
[10]	Yong-Chun Zhao(赵永春), Ming-Xin Zhu(朱铭鑫), Sheng-Shi Li(李胜世), and Ping Li(李萍). Room temperature quantum anomalous Hall insulator in honeycomb lattice, RuCS₃, with large magnetic anisotropy energy[J]. 中国物理B, 2023, 32(5): 57301-057301.
[11]	Chao Wu(吴超) and Chenhan Liu(刘晨晗). Effects of phonon bandgap on phonon-phonon scattering in ultrahigh thermal conductivity θ-phase TaN[J]. 中国物理B, 2023, 32(4): 46502-046502.
[12]	Dangqi Fang(方党旗). First-principles study of the bandgap renormalization and optical property of β-LiGaO₂[J]. 中国物理B, 2023, 32(4): 47101-047101.
[13]	Wenyu Xiang(相文雨), Yaping Wang(王亚萍), Weixiao Ji(纪维霄), Wenjie Hou(侯文杰),Shengshi Li(李胜世), and Peiji Wang(王培吉). Prediction of one-dimensional CrN nanostructure as a promising ferromagnetic half-metal[J]. 中国物理B, 2023, 32(3): 37103-037103.
[14]	Xiaoya Zhang(张晓雅), Yingjie Cheng(程莹洁), Chunyu Zhao(赵春宇), Jingwan Gao(高敬莞), Dongxiao Kan(阚东晓), Yizhan Wang(王义展), Duo Qi(齐舵), and Yingjin Wei(魏英进). Rational design of Fe/Co-based diatomic catalysts for Li-S batteries by first-principles calculations[J]. 中国物理B, 2023, 32(3): 36803-036803.
[15]	Chun-Sheng Hu(胡春生), Yun-Jing Wu(仵允京), Yuan-Shuo Liu(刘元硕), Shuai Fu(傅帅),Xiao-Ning Cui(崔晓宁), Yi-Hao Wang(王易昊), and Chang-Wen Zhang(张昌文). Single-layer intrinsic 2H-phase LuX₂ (X = Cl, Br, I) with large valley polarization and anomalous valley Hall effect[J]. 中国物理B, 2023, 32(3): 37306-037306.