物理化学学报 >> 2026, Vol. 42 >> Issue (4): 100224.doi: 10.1016/j.actphy.2025.100224

论文 上一篇    

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. 1 温州大学化学与材料工程学院, 浙江 温州 325035
    2 Department of Chemistry - ?ngstr?m 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
  • 收稿日期:2025-07-18 修回日期:2025-11-20 录用日期:2025-11-23 发布日期:2026-01-29
  • 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)
  • 作者简介:

    †这些作者对本工作做出了同等贡献

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

Jian Cao1, Chang Liu1, Danling Wang1, Haichao Li1, Lina Xu1,*(), Hongping Xiao1, Shaoqi Zhan2, Xiao He3,*(), Guoyong Fang1,*()   

  1. 1 College of Chemistry and Materials Engineering, Wenzhou University, Wenzhou 325035, Zhejiang Province, China
    2 Department of Chemistry - ?ngstr?m 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
  • Received:2025-07-18 Revised:2025-11-20 Accepted:2025-11-23 Published:2026-01-29
  • Contact: Email: xulina@wzu.edu.cn (Lina Xu)xiaohe@phy.ecnu.edu.cn (Xiao He)fanggy@wzu.edu.cn (Guoyong Fang)

RichHTML

17

PDF

269

赞

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: Ⅲ族氮化物, 机器学习势, 深度势能, 分子动力学, 热导率

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: Group-Ⅲ nitride, Machine learning potential, Deep potential, Molecular dynamics, Thermal conductivity