Accuracy of Machine Learning Potential for Predictions of Multiple-Target Physical Properties

doi:10.1088/0256-307X/37/12/126301

Chin. Phys. Lett.

2020, Vol. 37

Issue (12): 126301 DOI: 10.1088/0256-307X/37/12/126301

CONDENSED MATTER: STRUCTURE, MECHANICAL AND THERMAL PROPERTIES

Accuracy of Machine Learning Potential for Predictions of Multiple-Target Physical Properties

Yulou Ouyang¹, Zhongwei Zhang¹, Cuiqian Yu¹, Jia He¹, Gang Yan^1,2, and Jie Chen^1*

¹Center for Phononics and Thermal Energy Science, China–EU Joint Lab for Nanophononics, School of Physics Science and Engineering, Tongji University, Shanghai 200092, China
²Shanghai Institute of Intelligent Science and Technology, Tongji University, Shanghai 200092, China

Cite this article:

Yulou Ouyang, Zhongwei Zhang, Cuiqian Yu et al 2020 Chin. Phys. Lett. 37 126301

Download: PDF(1244KB) PDF(mobile)(1247KB) HTML
Export: BibTeX | EndNote | Reference Manager | ProCite | RefWorks

Abstract The accurate and rapid prediction of materials' physical properties, such as thermal transport and mechanical properties, are of particular importance for potential applications of featuring novel materials. We demonstrate, using graphene as an example, how machine learning potential, combined with the Boltzmann transport equation and molecular dynamics simulations, can simultaneously provide an accurate prediction of multiple-target physical properties, with an accuracy comparable to that of density functional theory calculation and/or experimental measurements. Benchmarked quantities include the Grüneisen parameter, the thermal expansion coefficient, Young's modulus, Poisson's ratio, and thermal conductivity. Moreover, the transferability of commonly used empirical potential in predicting multiple-target physical properties is also examined. Our study suggests that atomic simulation, in conjunction with machine learning potential, represents a promising method of exploring the various physical properties of novel materials.

Received: 26 September 2020 Published: 08 December 2020

PACS:	63.20.dk	(First-principles theory)
	63.20.kg	(Phonon-phonon interactions)

Fund: Supported by the National Natural Science Foundation of China (Grant Nos. 12075168 and 11890703), the Science and Technology Commission of Shanghai Municipality (Grant Nos. 19ZR1478600, 18ZR1442000 and 18JC1410900), the Fundamental Research Funds for the Central Universities (Grant No. 22120200069), and the Open Fund of Hunan Provincial Key Laboratory of Advanced Materials for New Energy Storage and Conversion (Grant No. 2018TP1037_201901).

TRENDMD:

URL:

https://cpl.iphy.ac.cn/10.1088/0256-307X/37/12/126301 OR https://cpl.iphy.ac.cn/Y2020/V37/I12/126301

Service
	E-mail this article
	E-mail Alert
	RSS
Articles by authors
	Yulou Ouyang
	Zhongwei Zhang
	Cuiqian Yu
	Jia He
	Gang Yan
	and Jie Chen

[1]	Zhang Z et al. 2020 Phys. Rep. 860 1
[2]	Xu W X and Liang X G 2020 Chin. Phys. Lett. 37 046601
[3]	Zhang Z and Chen J 2018 Chin. Phys. B 27 035101
[4]	Zhang Z et al. 2020 Phys. Rev. B 101 081402(R)
[5]	Ouyang Y et al. 2019 Ann. Phys. (Berlin) 531 1800437
[6]	Jiang P et al. 2020 J. Appl. Phys. 127 235101
[7]	Karplus M and McCammon J A 2002 Nat. Struct. Biol. 9 646
[8]	Durrant J D and McCammon J A 2011 BMC Syst. Biol. 9 71
[9]	Feng T et al. 2015 Innovative Food Sci. Emerging Technol. 31 1
[10]	Selvaraj C et al. 2018 Food Chem. Toxicol. 112 495
[11]	Chenoweth K, van D A C T and Goddard W A 2008 J. Phys. Chem. A 112 1040
[12]	Ishitani R et al. 2008 Proc. Natl. Acad. Sci. USA 105 15393
[13]	Ma Y et al. 2018 Carbon 135 263
[14]	Hu S et al. 2019 Nanoscale 11 11839
[15]	Zhang Z, Chen J and Li B 2017 Nanoscale 9 14208
[16]	Luo M and Dai L L 2007 J. Phys.: Condens. Matter 19 375109
[17]	Stillinger F H and Weber T A 1985 Phys. Rev. B 31 5262
[18]	Lindsay L and Broido D A 2010 Phys. Rev. B 81 205441
[19]	Tersoff J 1988 Phys. Rev. B 37 6991
[20]	Tersoff J 1989 Phys. Rev. B 39 5566
[21]	Daw M S and Baskes M I 1984 Phys. Rev. B 29 6443
[22]	MacDonald R A and MacDonald W M 1981 Phys. Rev. B 24 1715
[23]	Brenner D W et al. 2002 J. Phys.: Condens. Matter 14 783
[24]	Dyson A J and Smith P V 1996 Surf. Sci. 355 140
[25]	Ding B et al. 2020 Natl. Sci. Rev. nwaa220 (accepted)
[26]	Wang T et al. 2019 Adv. Funct. Mater. 30 1906041
[27]	Ju S and Shiomi J 2019 Nanoscale Microscale Thermophys. Eng. 23 157
[28]	Ju S et al. 2018 Phys. Rev. B 97 184305
[29]	Ju S et al. 2017 Phys. Rev. X 7 021024
[30]	Behler J 2017 Angew. Chem. Int. Ed. 56 12828
[31]	Balabin R M and Lomakina E I 2011 Phys. Chem. Chem. Phys. 13 11710
[32]	Bartók A P, Kondor R and Csányi G 2013 Phys. Rev. B 87 184115
[33]	Deringer V L and Csányi G 2017 Phys. Rev. B 95 094203
[34]	Bartók A P et al. 2018 Phys. Rev. X 8 041048
[35]	Thompson A P et al. 2015 J. Comput. Phys. 285 316
[36]	Shapeev A V 2016 Multiscale Model. Simul. 14 1153
[37]	Szlachta W J, Bartók A P and Csányi G 2014 Phys. Rev. B 90 104108
[38]	Jose K V J, Artrith N and Behler J 2012 J. Chem. Phys. 136 194111
[39]	Peterson A A 2016 J. Chem. Phys. 145 074106
[40]	Artrith N, Morawietz T and Behler J 2011 Phys. Rev. B 83 153101
[41]	Mortazavi B et al. 2020 J. Phys.: Mater. 3 02LT02
[42]	Zuo Y et al. 2020 J. Phys. Chem. A 124 731
[43]	Qian X and Yang R 2018 Phys. Rev. B 98 224108
[44]	Kresse G and Furthmuller J 1996 Comput. Mater. Sci. 6 15
[45]	Kresse G and Joubert D 1999 Phys. Rev. B 59 1758
[46]	Plimpton S 1995 J. Comput. Phys. 117 1
[47]	Chen J, Walther J H and Koumoutsakos P 2014 Nano Lett. 14 819
[48]	Grima J N et al. 2015 Adv. Mater. 27 1455
[49]	Jiang J W and Park H S 2016 Nano Lett. 16 2657
[50]	Qin H et al. 2017 Nanoscale 9 4135
[51]	Zhang Y Y et al. 2011 Carbon 49 4511
[52]	Jing N et al. 2012 RSC Adv. 2 9124
[53]	Togo A and Tanaka I 2015 Scr. Mater. 108 1
[54]	Li W et al. 2014 Comput. Phys. Commun. 185 1747
[55]	Qin G and Hu M 2018 npj Comput. Mater. 4 1
[56]	Togo A, Oba F and Tanaka I 2008 Phys. Rev. B 78 134106
[57]	The QUIP package is open to academic users at http://www.libatoms.org/home/software
[58]	Qian X et al. 2019 Mater. Today Phys. 10 100140
[59]	Rowe P et al. 2018 Phys. Rev. B 97 054303
[60]	Lee C et al. 2008 Science 321 385
[61]	Van L G et al. 2000 Chem. Phys. Lett. 326 181
[62]	Liu F, Ming P and Li J 2007 Phys. Rev. B 76 064120
[63]	Gui G, Li J and Zhong J 2008 Phys. Rev. B 78 075435
[64]	Sevik C 2014 Phys. Rev. B 89 035422
[65]	Mann S, Kumar R and Jindal V K 2017 RSC Adv. 7 22378
[66]	Lindsay L and Broido D A 2008 J. Phys.: Condens. Matter 20 165209
[67]	Holland M G 1964 Phys. Rev. 134 A471
[68]	Zhang Z et al. 2018 Carbon 139 289
[69]	Lindsay L et al. 2014 Phys. Rev. B 89 155426
[70]	Peng B et al. 2017 Nanoscale 9 7397
[71]	Feng T and Ruan X 2018 Phys. Rev. B 97 045202

Related articles from Frontiers Journals

[1]	Kun Luo, Baozhong Li, Lei Sun, Yingju Wu, Yanfeng Ge, Bing Liu, Julong He, Bo Xu, Zhisheng Zhao, and Yongjun Tian. Novel Boron Nitride Polymorphs with Graphite-Diamond Hybrid Structure[J]. Chin. Phys. Lett., 2022, 39(3): 126301
[2]	Chenqiang Hua, Hua Bai, Yi Zheng, Zhu-An Xu, Shengyuan A. Yang, Yunhao Lu, and Su-Huai Wei. Strong Coupled Magnetic and Electric Ordering in Monolayer of Metal Thio(seleno)phosphates[J]. Chin. Phys. Lett., 2021, 38(7): 126301
[3]	Ruoyun Lv, Xigui Yang, Dongwen Yang, Chunyao Niu, Chunxiang Zhao, Jinxu Qin, Jinhao Zang, Fuying Dong, Lin Dong, and Chongxin Shan. Computational Prediction of a Novel Superhard $sp^{3}$ Trigonal Carbon Allotrope with Bandgap Larger than Diamond[J]. Chin. Phys. Lett., 2021, 38(7): 126301
[4]	Kun Luo , Bing Liu , Lei Sun , Zhisheng Zhao, and Yongjun Tian . Design of a Class of New $sp^{2}$–$sp^{3}$ Carbons Constructed by Graphite and Diamond Building Blocks[J]. Chin. Phys. Lett., 2021, 38(2): 126301
[5]	Meng Li, Yuan Li, Chun-Yan Wang, Qiang Sun. Negative Thermal Expansion of GaFe(CN)$_{6}$ and Effect of Na Insertion by First-Principles Calculations[J]. Chin. Phys. Lett., 2019, 36(6): 126301
[6]	Lei Guo, Gang Tang, Jiawang Hong. Mechanical Properties of Formamidinium Halide Perovskites FABX$_{3}$ (FA=CH(NH$_{2})_{2}$; B=Pb, Sn; X=Br, I) by First-Principles Calculations[J]. Chin. Phys. Lett., 2019, 36(5): 126301
[7]	Qing Wang, Hai-Peng Wang, De-Lu Geng, Ming-Xing Li, Bing-Bo Wei. A Calorimetric Study Assisted with First Principle Calculations of Specific Heat for Si-Ge Alloys within a Broad Temperature Range[J]. Chin. Phys. Lett., 2018, 35(12): 126301
[8]	Pei GONG, Ya-Lin LI, Ya-Hui JIA, Xiao-Yong FANG. First Principle Study on Optical Properties of Tri-Group Doped (6,6) SiC Nanotubes[J]. Chin. Phys. Lett., 2018, 35(11): 126301
[9]	Zi-Wei Zhu, Ji-Yuan Zheng, Lai Wang, Bing Xiong, Chang-Zheng Sun, Zhi-Biao Hao, Yi Luo, Yan-Jun Han, Jian Wang, Hong-Tao Li. $Ab\ Initio$ Calculation of Dielectric Function in Wurtzite GaN Based on Walter's Model[J]. Chin. Phys. Lett., 2017, 34(3): 126301
[10]	Yu-Ping Cang, Shuai-Bin Lian, Hui-Ming Yang, Dong Chen. Predicting Physical Properties of Tetragonal, Monoclinic and Orthorhombic $M_{3}$N$_{4}$ ($M$=C, Si, Sn) Polymorphs via First-Principles Calculations[J]. Chin. Phys. Lett., 2016, 33(06): 126301
[11]	Jing-He Wu, Chang-Xin Liu. Ground-State Structure and Physical Properties of NB$_{2}$ Predicted from First Principles[J]. Chin. Phys. Lett., 2016, 33(03): 126301
[12]	Zhen-Ye Zhu, Si-Qi Wang, Yan-Ming Fu. First-Principles Study of Properties of Strained PbTiO$_{3}$/KTaO$_{3}$ Superlattice[J]. Chin. Phys. Lett., 2016, 33(02): 126301
[13]	ZHANG Jian, LI Hai-Tao, GUO Jun-Hong, HU Fang-Ren. Raman Scattering Modification Induced by Structural Change in Alumina Polymorphs[J]. Chin. Phys. Lett., 2015, 32(12): 126301
[14]	FENG Shi-Quan, LI Jun-Yu, CHENG Xin-Lu. The Structural, Dielectric, Lattice Dynamical and Thermodynamic Properties of Zinc-Blende CdX (X= S, Se, Te) from First-Principles Analysis[J]. Chin. Phys. Lett., 2015, 32(03): 126301
[15]	YU You, CHEN Chun-Lin, ZHAO Guo-Dong, ZHENG Xiao-Lin, ZHU Xing-Hua. Mechanical and Vibrational Properties of ZnS with Wurtzite Structure: A First-Principles Study[J]. Chin. Phys. Lett., 2014, 31(10): 126301

Viewed

Full text

Abstract