基于机器学习势的二维Ⅲ族氮化物性质预测

引用本文: 曹键, 刘畅, 王丹棱, 李海潮, 徐丽娜, 肖洪平, 詹绍琦, 何晓, 方国勇. 基于机器学习势的二维Ⅲ族氮化物性质预测[J]. 物理化学学报, 2026, 42(4): 100224. doi: 10.1016/j.actphy.2025.100224 shu

Citation: Jian Cao, Chang Liu, Danling Wang, Haichao Li, Lina Xu, Hongping Xiao, Shaoqi Zhan, Xiao He, Guoyong Fang. Machine learning potentials for property predictions of two-dimensional group-Ⅲ nitrides[J]. Acta Physico-Chimica Sinica, 2026, 42(4): 100224. doi: 10.1016/j.actphy.2025.100224 shu

基于机器学习势的二维Ⅲ族氮化物性质预测

曹键 ^{1, †,} ,
刘畅 ^{1, †,} ,
王丹棱 ^1, ,
李海潮 ^1, ,
徐丽娜 ^{1,
,} ,
肖洪平 ^1, ,
詹绍琦 ^2, ,
何晓 ^{3,
,} ,
方国勇 ^{1,
,}

1.
温州大学化学与材料工程学院, 浙江温州 325035
2.
Department of Chemistry - Ångström Laboratory, Uppsala University, Uppsala 75120, Sweden
3.
华东师范大学化学与分子工程学院, 上海分子治疗与新药创制工程技术研究中心, 上海市分子智造前沿科学研究基地, 上海 200062

通讯作者: Email: xulina@wzu.edu.cn (徐丽娜); xiaohe@phy.ecnu.edu.cn (何晓); fanggy@wzu.edu.cn (方国勇)

摘要: 二维Ⅲ族氮化物(h-BN、h-AlN、h-GaN与h-InN)因其类石墨烯结构、热稳定性及宽禁带特性，在电子与光电器件中具有重要潜力。传统的密度泛函理论(DFT)与经典分子动力学(MD)方法分别在计算精度与尺度有优势，但也限制了其在高精度的大尺度结构与性能研究中的应用。本文引入深度势能(DP)方法，构建了高精度机器学习势函数(MLP)，系统研究了二维Ⅲ族氮化物的晶格动力学、热力学、力学与热输运特性。深度势能对能量与原子力的预测接近GGA/PBE的精度，并准确重现了声子色散及0–1200 K范围内的热力学函数(自由能、热容、熵)。通过MD方法进行单轴拉伸模拟，揭示各材料的力学行为差异。h-BN刚性强且易脆断，h-AlN与h-GaN具有良好的强度和延展性，h-InN整体机械性能较弱。基于修正的非平衡分子动力学(NEMD)方法计算了材料热导率，发现h-BN与h-AlN表现出显著的长度依赖性，源于声子平均自由程较长。h-GaN与h-InN由于声子散射增强，热导率整体偏低。本研究结果表明，DP方法兼具GGA/PBE精度与大尺度模拟能力方面优势，不仅提升了对二维Ⅲ族氮化物结构性能的理解，也为其在材料设计和器件的应用提供了计算框架与理论依据。

关键词:

English

Machine learning potentials for property predictions of two-dimensional group-Ⅲ nitrides

Jian Cao ^{1, †,} ,
Chang Liu ^{1, †,} ,
Danling Wang ^1, ,
Haichao Li ^1, ,
Lina Xu ^{1,
,} ,
Hongping Xiao ^1, ,
Shaoqi Zhan ^2, ,
Xiao He ^{3,
,} ,
Guoyong Fang ^{1,
,}

1.
College of Chemistry and Materials Engineering, Wenzhou University, Wenzhou 325035, Zhejiang Province, China
2.
Department of Chemistry - Ångström Laboratory, Uppsala University, Uppsala 75120, Sweden
3.
Shanghai Engineering Research Center of Molecular Therapeutics and New Drug Development, Shanghai Frontiers Science Center of Molecule Intelligent Syntheses, School of Chemistry and Molecular Engineering, East China Normal University, Shanghai 200062, China

Corresponding author: Email: xulina@wzu.edu.cn (Lina Xu); xiaohe@phy.ecnu.edu.cn (Xiao He); fanggy@wzu.edu.cn (Guoyong Fang)

Received Date: 18 July 2025
Accepted Date: 23 November 2025
Revised Date: 20 November 2025
Available Online: 15 April 2026

Abstract: Due to the hexagonal structure, thermal stability, and wide bandgap, two-dimensional group-Ⅲ nitrides (h-BN, h-AlN, h-GaN and h-InN) show great promise for electronic and optoelectronic applications. Density functional theory (DFT) and classical molecular dynamics (MD) methods have advantages in calculation accuracy and scale respectively, but they are limited in the application of high-precision large-scale structure and performance research. Herein, we employ deep potential (DP) method to construct a high-precision machine learning potential (MLP) and systematically investigate the lattice dynamics, thermodynamic, mechanical, and thermal transport properties of two-dimensional Group Ⅲ nitrides. The DP method can achieve DFT accuracy in energy and atomic force predictions and accurately reproduce phonon dispersion and thermodynamic functions (free energy, heat capacity, entropy) across the 0–1200 K temperature range. MD simulations of uniaxial tensiles reveal distinct mechanical behavior differences among materials. h-BN exhibits high strength but brittle fracture characteristics, while h-AlN and h-GaN demonstrate good strength and ductility. h-InN shows relatively weak overall mechanical performance. Non-equilibrium MD simulations on thermal conductivity reveal significant length-dependent effects in h-BN and h-AlN, attributed to longer phonon mean free paths. Enhanced phonon scattering in h-GaN and h-InN results in lower thermal conductivities. These findings demonstrate that the DP method combines DFT accuracy with large-scale simulation capabilities can deepen understanding of structures and properties of two-dimensional Group Ⅲ nitrides and provide a computational framework and theoretical foundations for material design and device application.

Key words:

1. [1]
  F. Yang, L. Jin, L. Sun, X. Ren, X. Duan, H. Cheng, Adv. Mater. 30 (2018) 1801891, https://doi.org/10.1002/adma.201801891. doi: 10.1002/adma.201801891
2. [2]
  S. Lv, S. Wang, L. Li, S. Xie, J. Yu, Y. Zhong, G. Wang, C. Liang, X. Xu, L. Zhang, Adv. Sci. 10 (2023) 2300780, https://doi.org/10.1002/advs.202300780. doi: 10.1002/advs.202300780
3. [3]
  Y. Guo, H. Zhu, Q. Wang, ACS Appl. Mater. Interfaces 11 (2018) 1033, https://doi.org/10.1021/acsami.8b17341. doi: 10.1021/acsami.8b17341
4. [4]
  S. Z. Butler, S. M. Hollen, L. Cao, Y. Cui, J. A. Gupta, H. R. Gutiérrez, T. F. Heinz, S. S. Hong, J. Huang, A. F. Ismach, et al., ACS Nano 7 (2013) 2898, https://doi.org/10.1021/nn400280c. doi: 10.1021/nn400280c
5. [5]
  A. H. Castro Neto, F. Guinea, N. M. R. Peres, K. S. Novoselov, A. K. Geim, Rev. Mod. Phys. 81 (2009) 109, https://doi.org/10.1002/adfm.202107499. doi: 10.1002/adfm.202107499
6. [6]
  D. Deng, K. S. Novoselov, Q. Fu, N. Zheng, Z. Tian, X. Bao, Nat. Nanotechnol. 11 (2016) 218, https://doi.org/10.1038/nnano.2015.340. doi: 10.1038/nnano.2015.340
7. [7]
  A. Gupta, T. Sakthivel, S. Seal, Prog. Mater. Sci. 73 (2015) 44, https://doi.org/10.1016/j.pmatsci.2015.02.002. doi: 10.1016/j.pmatsci.2015.02.002
8. [8]
  M. Xu, T. Liang, M. Shi, H. Chen, Chem. Rev. 113 (2013) 3766, https://doi.org/10.1021/cr300263a. doi: 10.1021/cr300263a
9. [9]
  Q. Cui, G. Qin, W. Wang, K. R. Geethalakshmi, A. Du, Q. Sun, Appl. Surf. Sci. 500 (2020) 143993, https://doi.org/10.1016/j.apsusc.2019.143993. doi: 10.1016/j.apsusc.2019.143993
10. [10]
  M. Q. Yang, N. Zhang, Y. J. Xu, ACS Appl. Mater. Interfaces 5 (2013) 1156, https://doi.org/10.1021/am3029798. doi: 10.1021/am3029798
11. [11]
  K. Xia, V. I. Artyukhov, L. Sun, J. Zheng, L. Jiao, B. I. Yakobson, Y. Zhang, Nano Res. 9 (2016) 2182, https://doi.org/10.1007/s12274-016-1107-9. doi: 10.1007/s12274-016-1107-9
12. [12]
  A. D. Oyedele, S. Yang, L. Liang, A. A. Puretzky, K. Wang, J. Zhang, P. R. Pudasaini, A. W. Ghosh, Z. Liu, C. M. Rouleau, et al., J. Am. Chem. Soc. 139 (2017) 14090, https://doi.org/10.1021/jacs.7b04865. doi: 10.1021/jacs.7b04865
13. [13]
  M. Corso, W. Auwa, M. Muntwiler, A. Tamai, Science 303 (2004) 217, https://doi.org/10.1126/science.1091979. doi: 10.1126/science.1091979
14. [14]
  J. Yu, L. Wang, Z. Hao, Y. Luo, C. Sun, J. Wang, Y. Han, B. Xiong, H. Li, Adv. Mater. 32 (2020) 1903407, https://doi.org/10.1002/adma.201903407. doi: 10.1002/adma.201903407
15. [15]
  Z. Wang, G. Wang, X. Liu, S. Wang, T. Wang, S. Zhang, J. Yu, G. Zhao, L. Zhang, J. Mater. Chem. C 9 (2021) 17201, https://doi.org/10.1039/D1TC04022G. doi: 10.1039/D1TC04022G
16. [16]
  B. Pécz, G. Nicotra, F. Giannazzo, R. Yakimova, A. Koos, A. Kakanakova-Georgieva, Adv. Mater. 22 (2020) 2006660, https://doi.org/10.1002/adma.202006660. doi: 10.1002/adma.202006660
17. [17]
  I. A. Aleksandrov, T. V. Malin, K. S. Zhuravlev, S. V. Trubina, S. B. Erenburg, B. Pécz, Y. V. Lebiadok, Appl. Surf. Sci. 515 (2020) 146001, https://doi.org/10.1016/j.apsusc.2020.146001. doi: 10.1016/j.apsusc.2020.146001
18. [18]
  M. E. Khan, M. Aamir, C. Ming, Y. -Y. Sun, Y. -H. Kim, FlatChem 51 (2025) 100846, https://doi.org/10.1016/j.flatc.2025.100846. doi: 10.1016/j.flatc.2025.100846
19. [19]
  E. Sandre, A. Pasturel, Mol. Simul. 20 (1997) 63, https://doi.org/10.1080/08927029708024168. doi: 10.1080/08927029708024168
20. [20]
  R. Vink, G. Barkema, W. Van der Weg, N. Mousseau, J. Non-Cryst. Solids 282 (2001) 248, https://doi.org/10.1016/S0022-3093(01)00342-8. doi: 10.1016/S0022-3093(01)00342-8
21. [21]
  J. Tersoff, Phys. Rev. B 37 (1988) 6991, https://doi.org/10.1103/physrevb.37.6991. doi: 10.1103/physrevb.37.6991
22. [22]
  W. D. Cornell, P. Cieplak, C. I. Bayly, I. R. Gould, K. M. Merz Jr., D. M. Ferguson, D. C. Spellmeyer, T. Fox, J. W. Caldwell, P. A. Kollman, J. Am. Chem. Soc. 117 (1995) 5179, https://doi.org/10.1021/ja955032e. doi: 10.1021/ja955032e
23. [23]
  L. D. Schuler, X. Daura, W. F. van Gunsteren, J. Comput. Chem. 22 (2001) 1205, https://doi.org/10.1002/jcc.1078. doi: 10.1002/jcc.1078
24. [24]
  K. Wan, J. He, X. Shi, Adv. Mater. 36 (2023) 2305758, https://doi.org/10.1002/adma.202305758. doi: 10.1002/adma.202305758
25. [25]
  D. Shvets, A. Gorbatov, Eur. Phys. J. Plus 139 (2024) 8685, https://doi.org/10.1140/epjp/s13360-024-05685-z. doi: 10.1140/epjp/s13360-024-05685-z
26. [26]
  J. Xia, Y. Zhang, B. Jiang, Chem. Soc. Rev. 54 (2025) 4790, https://doi.org/10.1039/d5cs00104h. doi: 10.1039/d5cs00104h
27. [27]
  S. Hwang, J. Jung, C. Hong, W. Jeong, S. Kang, S. Han, J. Am. Chem. Soc. 145 (2023) 35, https://doi.org/10.1021/jacs.3c06210. doi: 10.1021/jacs.3c06210
28. [28]
  J. Behler, M. Parrinello, Phys. Rev. Lett. 98 (2007) 146401, https://doi.org/10.1103/PhysRevLett.98.146401. doi: 10.1103/PhysRevLett.98.146401
29. [29]
  A. P. Bartók, M. C. Payne, R. Kondor, G. Csányi, Phys. Rev. Lett. 104 (2010) 136403, https://doi.org/10.1103/PhysRevLett.104.136403. doi: 10.1103/PhysRevLett.104.136403
30. [30]
  M. A. Caro, Phys. Rev. B 100 (2019) 024112, https://doi.org/10.1103/PhysRevB.100.024112. doi: 10.1103/PhysRevB.100.024112
31. [31]
  J. Byggmästar, K. Nordlund, F. Djurabekova, Phys. Rev. Mater. 6 (2022) 083801, https://doi.org/10.1103/PhysRevMaterials.6.083801. doi: 10.1103/PhysRevMaterials.6.083801
32. [32]
  A. Thompson, L. Swiler, C. Trott, S. Foiles, G. Tucker, J. Comput. Phys. 285 (2015) 316, https://doi.org/10.1016/j.jcp.2014.12.018. doi: 10.1016/j.jcp.2014.12.018
33. [33]
  I. S. Novikov, K. Gubaev, E. V. Podryabinkin, A. V. Shapeev, Mach. Learn. : Sci. Technol. 2 (2020) 025002, https://doi.org/10.1088/2632-2153/abc9fe. doi: 10.1088/2632-2153/abc9fe
34. [34]
  L. Zhang, J. Han, H. Wang, R. Car, W. E, Phys. Rev. Lett. 120 (2018) 143001, https://doi.org/10.1103/physrevlett.120.143001. doi: 10.1103/physrevlett.120.143001
35. [35]
  R. Drautz, Phys. Rev. B 23 (2019) 249901, https://doi.org/10.1103/PhysRevB.100.249901. doi: 10.1103/PhysRevB.100.249901
36. [36]
  H. Dong, X. Wu, Y. Shi, P. Ying, W. Zhou, K. Xu, T. Liang, S. Xiong, S. Chen, Y. Wang, et al., J. Appl. Phys. 135 (2024) 161101, https://doi.org/10.1063/5.0200833. doi: 10.1063/5.0200833
37. [37]
  G. Kresse, J. Furthmüller, Phys. Rev. B 54 (1996) 11169, https://doi.org/10.1103/PhysRevB.54.11169. doi: 10.1103/PhysRevB.54.11169
38. [38]
  A. D. Becke, J. Chem. Phys. 96 (1992) 2155, https://doi.org/10.1063/1.462066. doi: 10.1063/1.462066
39. [39]
  J. P. Perdew, K. Burke, M. Ernzerhof, Phys. Rev. Lett. 77 (1996) 3865, https://doi.org/10.1103/physrevlett.77.3865. doi: 10.1103/physrevlett.77.3865
40. [40]
  J. Ben, X. Liu, C. Wang, Y. Zhang, Z. Shi, Y. Jia, S. Zhang, H. Zhang, W. Yu, D. Li, X. Sun, Adv. Mater. 32 (2021) 2006761, https://doi.org/10.1002/adma.202006761. doi: 10.1002/adma.202006761
41. [41]
  M. A. Qaeed, K. Ibrahim, K. M. A. Saron, A. Salhin, Superlattices Microstruct. 64 (2013) 77, https://doi.org/10.1016/j.spmi.2013.08.015. doi: 10.1016/j.spmi.2013.08.015
42. [42]
  A. Costales, M. A. Blanco, A. Martí, J. Am. Chem. Soc. 124 (2002) 4116, https://doi.org/10.1021/ja017380o. doi: 10.1021/ja017380o
43. [43]
  K. He, X. Zhang, S. Ren, J. Sun, arXiv: 1512.03385, https://doi.org/10.48550/arXiv.1512.03385.
44. [44]
  H. Wang, L. Zhang, J. Han, W. E, Comput. Phys. Commun. 228 (2018) 178, https://doi.org/10.1016/j.cpc.2018.03.016. doi: 10.1016/j.cpc.2018.03.016
45. [45]
  Y. Du, C. Hao, Z. Meng, C. Wang, K. Peng, Y. Tian, W. Duan, L. Yang, P. Lin, S. Zhang, Comput. Mater. Sci. 242 (2024) 113078, https://doi.org/10.1016/j.commatsci.2024.113078. doi: 10.1016/j.commatsci.2024.113078
46. [46]
  W. Yu, Z. Zhang, X. Wan, J. Su, Q. Gui, H. Guo, H. -x. Zhong, J. Robertson, Y. Guo, Chem. Mater. 35 (2023) 6651, https://doi.org/10.1021/acs.chemmater.3c00524. doi: 10.1021/acs.chemmater.3c00524
47. [47]
  W. Liang, G. Lu, J. Yu, J. Mater. Sci. Technol. 75 (2021) 78, https://doi.org/10.1016/j.jmst.2020.09.040. doi: 10.1016/j.jmst.2020.09.040
48. [48]
  D. J. Evans, B. L. Holian, J. Chem. Phys. 83 (1985) 406, https://doi.org/10.1063/1.449071. doi: 10.1063/1.449071
49. [49]
  A. P. Thompson, H. M. Aktulga, R. Berger, D. S. Bolintineanu, W. M. Brown, P. S. Crozier, P. J. in't Veld, A. Kohlmeyer, S. G. Moore, T. D. Nguyen, et al., Comput. Phys. Commun. 271 (2022) 108171, https://doi.org/10.1016/j.cpc.2021.108171. doi: 10.1016/j.cpc.2021.108171
50. [50]
  T. Gao, H. He, Y. Liu, Z. Bian, Q. Chen, Q. Xie, Y. Liang, Q. Xiao, Surf. Interfaces 39 (2023) 102983, https://doi.org/10.1016/j.surfin.2023.102983. doi: 10.1016/j.surfin.2023.102983
51. [51]
  K. Dey, S. Shahriar, M. A. R. Anan, P. Malakar, M. M. Rahman, M. M. Chowdhury, RSC Adv. 14 (2024) 24483, https://doi.org/10.1039/d4ra04814h. doi: 10.1039/d4ra04814h
52. [52]
  B. Mortazavi, M. Makaremi, M. Shahrokhi, Z. Fan, T. Rabczuk, Carbon 137 (2018) 57, https://doi.org/10.1016/j.carbon.2018.04.090. doi: 10.1016/j.carbon.2018.04.090
53. [53]
  F. Müller-Plathe, J. Chem. Phys. 106 (1997) 6082, https://doi.org/10.1063/1.473271. doi: 10.1063/1.473271
54. [54]
  A. Chernatynskiy, S. R. Phillpot, Phys. Rev. B 82 (2010) 134301, https://doi.org/10.1103/physrevb.82.134301. doi: 10.1103/physrevb.82.134301
55. [55]
  M. Ozsipahi, S. Jean, A. Beskok, A. A. Wilson, Int. Commun. Heat Mass Transf. 163 (2025) 108658, https://doi.org/10.1016/j.icheatmasstransfer.2025.108658. doi: 10.1016/j.icheatmasstransfer.2025.108658
56. [56]
  Y. Yang, J. Ma, J. Yang, Y. Zhang, ACS Appl. Mater. Interfaces 14 (2022) 45742, https://doi.org/10.1021/acsami.2c14871. doi: 10.1021/acsami.2c14871
57. [57]
  Z. Li, S. Xiong, C. Sievers, Y. Hu, Z. Fan, N. Wei, H. Bao, S. Chen, D. Donadio, T. Ala-Nissila, J. Chem. Phys. 151 (2019) 234105, https://doi.org/10.1063/1.5132543. doi: 10.1063/1.5132543
58. [58]
  L. Chaput, A. Togo, I. Tanaka, G. Hug, Phys. Rev. B 84 (2011) 094302, https://doi.org/10.1103/physrevb.84.094302. doi: 10.1103/physrevb.84.094302
59. [59]
  S. K. Achar, L. Zhang, J. K. Johnson, J. Phys. Chem. C 125 (2021) 14874, https://doi.org/10.1021/acs.jpcc.1c01411. doi: 10.1021/acs.jpcc.1c01411
60. [60]
  J. Callaway, Phys. Rev. 113 (1959) 1046, https://doi.org/10.1103/PhysRev.113.1046. doi: 10.1103/PhysRev.113.1046
61. [61]
  G. A. Slack, J. Phys. Chem. Solids 34 (1973) 321, https://doi.org/10.1016/0022-3697(73)90092-9. doi: 10.1016/0022-3697(73)90092-9
62. [62]
  N. A. Sakharova, A. F. G. Pereira, J. M. Antunes, Nanomaterials 14 (2024) 1736, https://doi.org/10.3390/nano14211736. doi: 10.3390/nano14211736

扫一扫看文章

计量

PDF下载量: 0
文章访问数: 219
HTML全文浏览量: 22

通讯作者: 陈斌, bchen63@163.com

1.
沈阳化工大学材料科学与工程学院沈阳 110142

基于机器学习势的二维Ⅲ族氮化物性质预测

通讯作者: Email: xulina@wzu.edu.cn (徐丽娜); xiaohe@phy.ecnu.edu.cn (何晓); fanggy@wzu.edu.cn (方国勇)

English

Machine learning potentials for property predictions of two-dimensional group-Ⅲ nitrides

Corresponding author: Email: xulina@wzu.edu.cn (Lina Xu); xiaohe@phy.ecnu.edu.cn (Xiao He); fanggy@wzu.edu.cn (Guoyong Fang)

CCS Chemistry：嵌段共聚物自组装成 “三明治”二维有机材料，实现纳米级压力传感功能

CCS Chemistry：颜徐州、鲍哲南：你的皮肤可能是一片SPMs

CCS Chemistry：工作高效不疲劳，只须让催化剂动起来

CCS Chemistry：静电组装导向聚合- 聚电解质纳米凝胶量化制备新策略

CCS Chemistry：金黄色葡萄球菌醛基脱氢酶是如何识别特异性底物的？

计量

通讯作者: 陈斌, bchen63@163.com

中国化学会秘书处

基于机器学习势的二维Ⅲ族氮化物性质预测

通讯作者: Email: xulina@wzu.edu.cn (徐丽娜); xiaohe@phy.ecnu.edu.cn (何晓); fanggy@wzu.edu.cn (方国勇)

English

Machine learning potentials for property predictions of two-dimensional group-Ⅲ nitrides

Corresponding author: Email: xulina@wzu.edu.cn (Lina Xu); xiaohe@phy.ecnu.edu.cn (Xiao He); fanggy@wzu.edu.cn (Guoyong Fang)

CCS Chemistry：嵌段共聚物自组装成 “三明治”二维有机材料，实现纳米级压力传感功能

CCS Chemistry：颜徐州、鲍哲南： 你的皮肤可能是一片SPMs

CCS Chemistry：工作高效不疲劳，只须让催化剂动起来

CCS Chemistry：静电组装导向聚合- 聚电解质纳米凝胶量化制备新策略

CCS Chemistry：金黄色葡萄球菌醛基脱氢酶是如何识别特异性底物的？

计量

文章相关

通讯作者: 陈斌, bchen63@163.com

中国化学会秘书处

CCS Chemistry：颜徐州、鲍哲南：你的皮肤可能是一片SPMs