面向铁电相变的机器学习: 基于图卷积神经网络的分子动力学模拟

欧阳鑫健; 张岩星; 王之龙; 张锋; 陈韦嘉; 庄园; 揭晓; 刘来君; 王大威

doi:10.7498/aps.73.20240156

摘要

铁电材料广泛应用于功能器件中, 对铁电体进行方便、准确的理论建模, 是一个长期被关注的问题. 本文提出了一种基于图卷积神经网络的铁电相变模拟方法, 利用图卷积神经网络对铁电材料的势能面进行原子层面的建模, 并将得到的神经网络势函数作为计算器, 以驱动大体系的分子动力学模拟. 给定原子位置, 训练好的图卷积神经网络能够给出势能的高精度预测, 达到每原子1 meV级别, 与从头算(ab inito)精度基本相当, 同时在计算速度上相比从头算方法有数个数量级的提升. 得益于神经网络的高精度和快速预测能力, 结合分子动力学模拟, 本文对两种不同类型的铁电材料——GeTe和CsSnI₃进行研究, 成功模拟了它们随温度发生的结构相变, 模拟结果和实验相符合. 这些结果说明了图卷积神经网络在铁电体建模和相变模拟应用中的准确性和可靠性, 为铁电体的理论探索提供了一个通用建模方法.

关键词:

铁电相变 /
机器学习 /
势函数

Abstract

Ferroelectric materials are widely used in functional devices, however, it has been a long-standing issue to achieve convenient and accurate theoretical modeling of them. Herein, a noval approach to modeling ferroelectric materials is proposed by using graph convolutional neural networks (GCNs). In this approach, the potential energy surface of ferroelectric materials is described by GCNs, which then serves as a calculator to conduct large-scale molecular dynamics simulations. Given atomic positions, the well-trained GCN model can provide accurate predictions of the potential energy and atomic forces, with an accuracy reaching up to 1 meV per atom. The accuracy of GCNs is comparable to that of ab inito calculations, while the computing speed is faster than that of ab inito calculations by a few orders. Benefiting from the high accuracy and fast prediction of the GCN model, we further combine it with molecular dynamics simulations to investigate two representative ferroelectric materials—bulk GeTe and CsSnI₃, and successfully produce their temperature-dependent structural phase transitions, which are in good agreement with the experimental observations. For GeTe, we observe an unusual negative thermal expansion around the region of its ferroelectric phase transition, which has been reported in previous experiments. For CsSnI₃, we correctly obtain the octahedron tilting patterns associated with its phase transition sequence. These results demonstrate the accuracy and reliability of GCNs in the modeling of potential energy surfaces for ferroelectric materials, thus providing a universal approach for investigating them theoretically.

Keywords:

作者及机构信息

1.
西安交通大学电子与信息学部微电子学院, 西安　710049

2.
河南师范大学物理学院, 新乡　453007

3.
桂林理工大学材料科学与工程学院, 桂林　541004

通信作者: 王大威, dawei.wang@xjtu.edu.cn

基金项目: 国家自然科学基金(批准号: 11974268, 12111530061)资助的课题.

Authors and contacts

1.
School of Microelectronics, Faculty of Electronics and Information Engineering, Xi’an Jiaotong University, Xi’an 710049, China

2.
School of Physics, Henan Normal University, Xinxiang 453007, China

3.
College of Materials Science and Engineering, Guilin University of Technology, Guilin 541004, China

Corresponding author: Wang Da-Wei, dawei.wang@xjtu.edu.cn

Funds: Project supported by the National Natural Science Foundation of China (Grant Nos. 11974268, 12111530061).

文章全文 : translate this paragraph

参考文献

[1]	Martin L W, Rappe A M 2016 Nat. Rev. Mater. 2 16087 Google Scholar
[2]	Pal S, Sarath N, Priya K S, Murugavel P 2022 J. Phys. D: Appl. Phys. 55 283001 Google Scholar
[3]	Qi L, Ruan S, Zeng Y J 2021 Adv. Mater. 33 2005098 Google Scholar
[4]	欧阳鑫健, 张紫阳, 张锋, 张佳乐, 王大威 2023 72 057502 Google Scholar Ouyang X J, Zhang Z Y, Zhang F, Zhang J L, Wang D W 2023 Acta Phys. Sin. 72 057502 Google Scholar
[5]	Zhong W, Vanderbilt D, Rabe K M 1994 Phys. Rev. Lett. 73 1861 Google Scholar
[6]	Zhong W, Vanderbilt D, Rabe K M 1995 Phys. Rev. B 52 6301 Google Scholar
[7]	Sepliarsky M, Wu Z, Asthagiri A, Cohen R E 2004 Ferroelectrics 301 55 Google Scholar
[8]	Wu H H, Cohen R E 2017 Phys. Rev. B 96 054116 Google Scholar
[9]	Behler J 2016 J. Chem. Phys. 145 170901 Google Scholar
[10]	Behler J, Csányi G 2021 Eur. Phys. J. B 94 142 Google Scholar
[11]	Mueller T, Hernandez A, Wang C 2020 J. Chem. Phys. 152 050902 Google Scholar
[12]	Kang P L, Shang C, Liu Z P 2020 Acc. Chem. Res. 53 2119 Google Scholar
[13]	曾启昱, 陈博, 康冬冬, 戴佳钰 2023 72 187102 Google Scholar Zeng Q Y, Chen B, Kang D D, Dai J Y 2023 Acta Phys. Sin. 72 187102 Google Scholar
[14]	张嘉晖 2024 73 069301 Google Scholar Zhang J H 2024 Acta Phys. Sin. 73 069301 Google Scholar
[15]	LeCun Y, Bengio Y, Hinton G 2015 Nature 521 436 Google Scholar
[16]	Gilmer J, Schoenholz S S, Riley P F, Vinyals O, Dahl G E 2017 Proceedings of the 34th International Conference on Machine Learning Sydney, Australia, August 6–11, 2017 p1263
[17]	Schütt K T, Sauceda H E, Kindermans P J, Tkatchenko A, Müller K R 2018 J. Chem. Phys. 148 241722 Google Scholar
[18]	Ouyang X J, Chen W J, Zhang Y X, Zhang F, Zhuang Y, Jie X, Liu L J, Wang D W 2023 Phys. Rev. B 108 L020103 Google Scholar
[19]	Ouyang X J, Zhuang Y, Zhang J L, Zhang F, Jie X, Chen W J, Zhang Y X, Liu L J, Wang D W 2023 J. Phys. Chem. C 127 20890 Google Scholar
[20]	Kong J G, Li Q X, Li J, Liu Y, Zhu J J 2022 Chin. Phys. Lett. 39 067503 Google Scholar
[21]	Gasteiger J, Groß J, Günnemann S 2020 International Conference on Learning Representations Virtual, April 26–May 1, 2020
[22]	Gasteiger J, Giri S, Margraf J T, Günnemann S 2020 Machine Learning for Molecules Workshop, NeurIPS Virtual, December 6–12, 2020
[23]	Chattopadhyay T, Boucherle J X, vonSchnering H G 1987 J. Phys. C: Solid State Phys. 20 1431 Google Scholar
[24]	Dangić D, Murphy A R, Murray E D, Fahy S, Savić I 2018 Phys. Rev. B 97 224106 Google Scholar
[25]	Yamada K, Funabiki S, Horimoto H, Matsui T, Okuda T, Ichiba S 1991 Chem. Lett. 20 801 Google Scholar
[26]	da Silva E L, Skelton J M, Parker S C, Walsh A 2015 Phys. Rev. B 91 144107 Google Scholar
[27]	Schütt K, Unke O, Gastegger M 2021 Proceedings of the 38th International Conference on Machine Learning Virtual, July 18–24, 2021 p9377
[28]	He K, Zhang X, Ren S, Sun J 2016 Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Las Vegas, USA, June 27–30, 2016 p770
[29]	Musaelian A, Batzner S, Johansson A, Sun L, Owen C J, Kornbluth M, Kozinsky B 2023 Nat. Commun. 14 579 Google Scholar
[30]	Paszke A, Gross S, Massa F, Lerer A, Bradbury J, Chanan G, Killeen T, Lin Z, Gimelshein N, Antiga L, Desmaison A, Kopf A, Yang E, DeVito Z, Raison M, Tejani A, Chilamkurthy S, Steiner B, Fang L, Bai J, Chintala S 2019 33rd Conference on Neural Information Processing Systems Vancouver, Canada, December 8–14, 2019 p8026
[31]	Batzner S, Musaelian A, Sun L, Geiger M, Mailoa J P, Kornbluth M, Molinari N, Smidt T E, Kozinsky B 2022 Nat. Commun. 13 2453 Google Scholar
[32]	Frenkel D, Smit B 2002 Understanding Molecular Simulation: from Algorithms to Applications (Amsterdam: Elsevier
[33]	Blöchl P E 1994 Phys. Rev. B 50 17953 Google Scholar
[34]	Kresse G, Furthmüller J 1996 Phys. Rev. B 54 11169 Google Scholar
[35]	Enkovaara J, Rostgaard C, Mortensen J J, et al. 2010 J. Phys.: Condens. Matter 22 253202 Google Scholar
[36]	Perdew J P, Burke K, Ernzerhof M 1996 Phys. Rev. Lett. 77 3865 Google Scholar
[37]	Melchionna S, Ciccotti G, Lee Holian B 1993 Mol. Phys. 78 533 Google Scholar
[38]	Melchionna S 2000 Phys. Rev. E 61 6165 Google Scholar
[39]	Larsen A H, Mortensen J J, Blomqvist J, et al. 2017 J. Phys.: Condens. Matter 29 273002 Google Scholar
[40]	Smith J S, Nebgen B, Lubbers N, Isayev O, Roitberg A E 2018 J. Chem. Phys. 148 241733 Google Scholar
[41]	Nielsen O H, Martin R M 1985 Phys. Rev. B 32 3780 Google Scholar
[42]	Thompson A P, Plimpton S J, Mattson W 2009 J. Chem. Phys. 131 154107 Google Scholar
[43]	Loshchilov I, Hutter F 2019 7th International Conference on Learning Representations New Orleans, USA, May 6–9, 2019
[44]	Singh K, Kumari S, Singh H, Bala N, Singh P, Kumar A, Thakur A 2023 Appl. Nanosci. 13 95 Google Scholar
[45]	Fan Z, Qu J, Wang T, Wen Y, An Z, Jiang Q, Xue W, Zhou P, Xu X 2023 Chin. Phys. B 32 128508 Google Scholar
[46]	Chung I, Song J H, Im J, Androulakis J, Malliakas C D, Li H, Freeman A J, Kenney J T, Kanatzidis M G 2012 J. Am. Chem. Soc. 134 8579 Google Scholar
[47]	Shum K, Chen Z, Qureshi J, Yu C, Wang J J, Pfenninger W, Vockic N, Midgley J, Kenney J T 2010 Appl. Phys. Lett. 9 6
[48]	Stoumpos C C, Kanatzidis M G 2015 Acc. Chem. Res 48 2791 Google Scholar
[49]	Savory C N, Walsh A, Scanlon D O 2016 ACS Energy Lett. 1 949 Google Scholar
[50]	Quan L N, García de Arquer F P, Sabatini R P, Sargent E H 2018 Adv. Mater. 30 1801996 Google Scholar
[51]	Heidari Gourji F, Velauthapillai D 2021 Molecules 26 2010 Google Scholar
[52]	Glazer A M 1972 Acta Crystallogr., Sect. B Struct. Crystallogr. Cryst. Chem. 28 3384 Google Scholar
[53]	Xie N, Zhang J, Raza S, Zhang N, Chen X, Wang D 2020 J. Phys.: Condens. Matter. 32 315901 Google Scholar
[54]	King-Smith R D, Vanderbilt D 1993 Phys. Rev. B 47 1651 Google Scholar
[55]	Resta R, Vanderbilt D 2007 Theory of Polarization: A Modern Approach (Berlin: Springer) p31
[56]	Schubert K, Fricke H 1951 Zeitschrift für Naturforschung A 6 781
[57]	Wdowik U D, Parlinski K, Rols S, Chatterji T 2014 Phys. Rev. B 89 224306 Google Scholar
[58]	Goldak J, Barrett C, Innes D, Youdelis W 1966 J. Chem. Phys. 44 3323 Google Scholar
[59]	Gonze X, Amadon B, Anglade P M, et al. 2009 Comput. Phys. Commun. 180 2582 Google Scholar
[60]	Ciucivara A, Sahu B R, Kleinman L 2006 Phys. Rev. B 73 214105 Google Scholar
[61]	Shaltaf R, Gonze X, Cardona M, Kremer R K, Siegle G 2009 Phys. Rev. B 79 075204 Google Scholar
[62]	Dangić D, Fahy S, Savić I 2022 Phys. Rev. B 106 134113 Google Scholar
[63]	Bechtel J S, Van der Ven A 2018 Phys. Rev. Mater. 2 025401 Google Scholar
[64]	Rabe K M, Joannopoulos J D 1987 Phys. Rev. B 36 6631 Google Scholar
[65]	Kooi B J, Wuttig M 2020 Adv. Mater. 32 1908302 Google Scholar
[66]	Ye Q J, Liu Z Y, Feng Y, Gao P, Li X Z 2018 Phys. Rev. Lett. 121 135702 Google Scholar
[67]	吕程烨, 陈英炜, 谢牧廷, 李雪阳, 于宏宇, 钟阳, 向红军 2023 72 237102 Google Scholar Lü C Y, Chen Y W, Xie M T, Li X Y, Yu H Y, Zhong Y, Xiang H J 2023 Acta Phys. Sin. 72 237102 Google Scholar
[68]	Zhang J L, Zhang F, Wei D N, Liu L, Liu X, Fang D, Zhang G X, Chen X, Wang D W 2022 Phys. Rev. B 105 094116 Google Scholar
[69]	Chang K, Liu J, Lin H, Wang N, Zhao K, Zhang A, Jin F, Zhong Y, Hu X, Duan W, Zhang Q, Fu L, Xue Q K, Chen X, Ji S H 2016 Science 353 274 Google Scholar
[70]	Wang B, Novendra N, Navrotsky A 2019 J. Am. Chem. Soc. 141 14501 Google Scholar
[71]	Gao L, Yadgarov L, Sharma R, Korobko R, McCall K M, Fabini D H, Stoumpos C C, Kanatzidis M G, Rappe A M, Yaffe O 2021 Mater. Adv. 2 4610 Google Scholar
[72]	Lee J H, Bristowe N C, Lee J H, Lee S H, Bristowe P D, Cheetham A K, Jang H M 2016 Chem. Mater. 28 4259 Google Scholar
[73]	Chen L, Xu B, Yang Y, Bellaiche L 2020 Adv. Funct. Mater. 30 1909496 Google Scholar
[74]	Jinnouchi R, Lahnsteiner J, Karsai F, Kresse G, Bokdam M 2019 Phys. Rev. Lett. 122 225701 Google Scholar
[75]	Bartók A P, Payne M C, Kondor R, Csányi G 2010 Phys. Rev. Lett. 104 136403 Google Scholar
[76]	Wang D W, Bokov A A, Ye Z G, Hlinka J, Bellaiche L 2016 Nat. Commun. 7 11014 Google Scholar
[77]	Wang D W, Liu L J, Liu J, Zhang N, Wei X Y 2018 Chin. Phys. B 27 127702 Google Scholar
[78]	Cohen A, Brenner T M, Klarbring J, Sharma R, Fabini D H, Korobko R, Nayak P K, Hellman O, Yaffe O 2022 Adv. Mater. 34 2107932 Google Scholar
[79]	Zhang L, Han J, Wang H, Car R, E W 2018 Phys. Rev. Lett. 120 143001 Google Scholar
[80]	Gu H Y, Yin W J, Gong X G 2021 Appl. Phys. Lett. 119 191101 Google Scholar
[81]	陈基, 冯页新, 李新征, 王恩哥 2015 64 183101 Google Scholar Chen J, Feng Y X, Li X Z, Wang E G 2015 Acta Phys. Sin. 64 183101 Google Scholar
[82]	Zhang Y, Sun J, Perdew J P, Wu X 2017 Phys. Rev. B 96 035143 Google Scholar
[83]	Wu Z, Cohen R E, Singh D J 2004 Phys. Rev. B 70 104112 Google Scholar
[84]	Yuk S F, Pitike K C, Nakhmanson S M, Eisenbach M, Li Y W, Cooper V R 2017 Sci. Rep. 7 43482 Google Scholar

施引文献

图 1 方法流程图, 包括从头算分子动力学(ab inito molecular dynamics, AIMD)采样、图卷积神经网络(graph convolutional neural network, GCN)搭建和分子动力学模拟三个部分

Fig. 1. Workflow of this study, including ab inito molecular dynamics (AIMD) sampling, graph convolutional neural network (GCN) construction and MD simulations.

下载: 全尺寸图片幻灯片

图 2 (a)图卷积神经网络框架, 以改进后的DimeNet++为例. 各个模块的具体结构和文献[22]一致; (b)相互作用模块, 包括消息传递$ f_{{\rm{inter}}} $和消息更新$ f_{{\rm{update}}} $两个过程

Fig. 2. (a) Architecture of the GCN model, a refined DimeNet++, where the design of blocks are inherited from Reference [22]; (b) interaction blocks, including message interaction and message update functions.

下载: 全尺寸图片幻灯片

图 3 (a) GeTe和(b) CsSnI₃的DFT数据集的能量分布柱状图, 以优化后的立方相的能量为能量零点

Fig. 3. The energy distribution for the data sets of (a) GeTe and (b) CsSnI₃ relative to the energy of corresponding cubic phase.

下载: 全尺寸图片幻灯片

图 4 图卷积神经网络模型(GCN)关于GeTe ((a), (b))和CsSnI₃ ((c), (d))的测试集和验证集势阱预测效果, 以优化后的立方相结构为能量零点

Fig. 4. The test and validation results of the trained graph convolutional neural network (GCN) models for GeTe ((a), (b)) and CsSnI₃ ((c), (d)) respectively, where the energy of the optimized cubic phase is set as the reference energy.

下载: 全尺寸图片幻灯片

图 5 GeTe块体的相变模拟结果　(a)晶格常数随温度发生的变化, 红色虚线框表示铁电相变附近负的热膨胀效应; (b) Ge原子和Te原子两者沿$ x, y, z $三个方向的平均相对位移(虚线)及其模长(黑色实线)、自发极化(红色实线)随温度的变化情况; (c) Ge原子和Te原子的平均相对位移随体系大小的收敛性测试

Fig. 5. Phase transition simulations for bulk GeTe: (a) The temperature-dependence of simulated lattice parameters, where the red area indicates the negative volumetric thermal expansion of GeTe near the phase transition; (b) the average relative displacements between Ge and Te atoms during MD simulations and the spontaneous polarization; (c) the convergence of simulation with respect to the system size.

下载: 全尺寸图片幻灯片

图 6 CsSnI₃块体的相变模拟结果　(a)晶格常数随温度发生的变化; (b) CsSnI₃在立方相(C)、四方相(T)和正交相(O)下的八面体转动情况, OOP (out-of-phase)和IP (in-phase)分别表示反相和同相转动

Fig. 6. Phase transition simulations for bulk CsSnI₃: (a) The temperature-dependence of simulated lattice parameters; (b) the change of SnI₆ octahedron tilting pattern during the cubic-tetragonal-orthorhombic (C-T-O) phase transition.

下载: 全尺寸图片幻灯片

表 1 GeTe和CsSnI₃的图卷积神经网络模型在各自测试集上的精度

Table 1. Prediction accuracy of the trained GCN models for GeTe and CsSnI₃ on their test data sets

单位	能量	力	应力
单位	/(meV·atom^–1)	/(meV·Å^–1·atom^–1)	/(meV·Å^–3)
GeTe	0.197	1.016	2.371
CsSnI₃	0.323	0.825	0.944

下载: 导出CSV

表 2 图卷积神经网络(GCN)分别用于GeTe和CsSnI₃的结构优化结果

Table 2. The structure optimization for GeTe and CsSnI₃ using their corresponding graph convolutional neural network (GCN) models

	Phases		a/Å	b/Å	c/Å	α/(°)	β/(°)	γ/(°)
GeTe	$ Fm\bar{3}m $	DFT	5.997	5.997	5.997	90	90	90
		GCN	5.996	5.996	5.996	90	90	90
		error	0.017%	0.017%	0.017%	0%	0%	0%
	$ R3 m $	DFT	6.076	6.076	6.076	88.04	88.04	88.04
		GCN	6.061	6.061	6.061	88.37	88.37	88.37
		error	0.244%	0.244%	0.244%	0.375%	0.375%	0.375%
CsSnI₃	$ Pm\bar{3}m $	DFT	6.270	6.270	6.270	90	90	90
		GCN	6.270	6.270	6.270	90	90	90
		error	0%	0%	0%	0%	0%	0%
	$ P4/mbm $	DFT	6.337	6.224	6.224	90	90	90
		GCN	6.346	6.211	6.211	90	90	90
		error	0.148%	0.195%	0.195%	0%	0%	0%
	$ Pnma $	DFT	6.243	6.243	6.254	90	90	89.63
		GCN	6.225	6.225	6.235	90	90	89.72
		error	0.295%	0.295%	0.311%	0%	0%	0.103%

下载: 导出CSV

map

[1]	Martin L W, Rappe A M 2016 Nat. Rev. Mater. 2 16087 Google Scholar
[2]	Pal S, Sarath N, Priya K S, Murugavel P 2022 J. Phys. D: Appl. Phys. 55 283001 Google Scholar
[3]	Qi L, Ruan S, Zeng Y J 2021 Adv. Mater. 33 2005098 Google Scholar
[4]	欧阳鑫健, 张紫阳, 张锋, 张佳乐, 王大威 2023 72 057502 Google Scholar Ouyang X J, Zhang Z Y, Zhang F, Zhang J L, Wang D W 2023 Acta Phys. Sin. 72 057502 Google Scholar
[5]	Zhong W, Vanderbilt D, Rabe K M 1994 Phys. Rev. Lett. 73 1861 Google Scholar
[6]	Zhong W, Vanderbilt D, Rabe K M 1995 Phys. Rev. B 52 6301 Google Scholar
[7]	Sepliarsky M, Wu Z, Asthagiri A, Cohen R E 2004 Ferroelectrics 301 55 Google Scholar
[8]	Wu H H, Cohen R E 2017 Phys. Rev. B 96 054116 Google Scholar
[9]	Behler J 2016 J. Chem. Phys. 145 170901 Google Scholar
[10]	Behler J, Csányi G 2021 Eur. Phys. J. B 94 142 Google Scholar
[11]	Mueller T, Hernandez A, Wang C 2020 J. Chem. Phys. 152 050902 Google Scholar
[12]	Kang P L, Shang C, Liu Z P 2020 Acc. Chem. Res. 53 2119 Google Scholar
[13]	曾启昱, 陈博, 康冬冬, 戴佳钰 2023 72 187102 Google Scholar Zeng Q Y, Chen B, Kang D D, Dai J Y 2023 Acta Phys. Sin. 72 187102 Google Scholar
[14]	张嘉晖 2024 73 069301 Google Scholar Zhang J H 2024 Acta Phys. Sin. 73 069301 Google Scholar
[15]	LeCun Y, Bengio Y, Hinton G 2015 Nature 521 436 Google Scholar
[16]	Gilmer J, Schoenholz S S, Riley P F, Vinyals O, Dahl G E 2017 Proceedings of the 34th International Conference on Machine Learning Sydney, Australia, August 6–11, 2017 p1263
[17]	Schütt K T, Sauceda H E, Kindermans P J, Tkatchenko A, Müller K R 2018 J. Chem. Phys. 148 241722 Google Scholar
[18]	Ouyang X J, Chen W J, Zhang Y X, Zhang F, Zhuang Y, Jie X, Liu L J, Wang D W 2023 Phys. Rev. B 108 L020103 Google Scholar
[19]	Ouyang X J, Zhuang Y, Zhang J L, Zhang F, Jie X, Chen W J, Zhang Y X, Liu L J, Wang D W 2023 J. Phys. Chem. C 127 20890 Google Scholar
[20]	Kong J G, Li Q X, Li J, Liu Y, Zhu J J 2022 Chin. Phys. Lett. 39 067503 Google Scholar
[21]	Gasteiger J, Groß J, Günnemann S 2020 International Conference on Learning Representations Virtual, April 26–May 1, 2020
[22]	Gasteiger J, Giri S, Margraf J T, Günnemann S 2020 Machine Learning for Molecules Workshop, NeurIPS Virtual, December 6–12, 2020
[23]	Chattopadhyay T, Boucherle J X, vonSchnering H G 1987 J. Phys. C: Solid State Phys. 20 1431 Google Scholar
[24]	Dangić D, Murphy A R, Murray E D, Fahy S, Savić I 2018 Phys. Rev. B 97 224106 Google Scholar
[25]	Yamada K, Funabiki S, Horimoto H, Matsui T, Okuda T, Ichiba S 1991 Chem. Lett. 20 801 Google Scholar
[26]	da Silva E L, Skelton J M, Parker S C, Walsh A 2015 Phys. Rev. B 91 144107 Google Scholar
[27]	Schütt K, Unke O, Gastegger M 2021 Proceedings of the 38th International Conference on Machine Learning Virtual, July 18–24, 2021 p9377
[28]	He K, Zhang X, Ren S, Sun J 2016 Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Las Vegas, USA, June 27–30, 2016 p770
[29]	Musaelian A, Batzner S, Johansson A, Sun L, Owen C J, Kornbluth M, Kozinsky B 2023 Nat. Commun. 14 579 Google Scholar
[30]	Paszke A, Gross S, Massa F, Lerer A, Bradbury J, Chanan G, Killeen T, Lin Z, Gimelshein N, Antiga L, Desmaison A, Kopf A, Yang E, DeVito Z, Raison M, Tejani A, Chilamkurthy S, Steiner B, Fang L, Bai J, Chintala S 2019 33rd Conference on Neural Information Processing Systems Vancouver, Canada, December 8–14, 2019 p8026
[31]	Batzner S, Musaelian A, Sun L, Geiger M, Mailoa J P, Kornbluth M, Molinari N, Smidt T E, Kozinsky B 2022 Nat. Commun. 13 2453 Google Scholar
[32]	Frenkel D, Smit B 2002 Understanding Molecular Simulation: from Algorithms to Applications (Amsterdam: Elsevier
[33]	Blöchl P E 1994 Phys. Rev. B 50 17953 Google Scholar
[34]	Kresse G, Furthmüller J 1996 Phys. Rev. B 54 11169 Google Scholar
[35]	Enkovaara J, Rostgaard C, Mortensen J J, et al. 2010 J. Phys.: Condens. Matter 22 253202 Google Scholar
[36]	Perdew J P, Burke K, Ernzerhof M 1996 Phys. Rev. Lett. 77 3865 Google Scholar
[37]	Melchionna S, Ciccotti G, Lee Holian B 1993 Mol. Phys. 78 533 Google Scholar
[38]	Melchionna S 2000 Phys. Rev. E 61 6165 Google Scholar
[39]	Larsen A H, Mortensen J J, Blomqvist J, et al. 2017 J. Phys.: Condens. Matter 29 273002 Google Scholar
[40]	Smith J S, Nebgen B, Lubbers N, Isayev O, Roitberg A E 2018 J. Chem. Phys. 148 241733 Google Scholar
[41]	Nielsen O H, Martin R M 1985 Phys. Rev. B 32 3780 Google Scholar
[42]	Thompson A P, Plimpton S J, Mattson W 2009 J. Chem. Phys. 131 154107 Google Scholar
[43]	Loshchilov I, Hutter F 2019 7th International Conference on Learning Representations New Orleans, USA, May 6–9, 2019
[44]	Singh K, Kumari S, Singh H, Bala N, Singh P, Kumar A, Thakur A 2023 Appl. Nanosci. 13 95 Google Scholar
[45]	Fan Z, Qu J, Wang T, Wen Y, An Z, Jiang Q, Xue W, Zhou P, Xu X 2023 Chin. Phys. B 32 128508 Google Scholar
[46]	Chung I, Song J H, Im J, Androulakis J, Malliakas C D, Li H, Freeman A J, Kenney J T, Kanatzidis M G 2012 J. Am. Chem. Soc. 134 8579 Google Scholar
[47]	Shum K, Chen Z, Qureshi J, Yu C, Wang J J, Pfenninger W, Vockic N, Midgley J, Kenney J T 2010 Appl. Phys. Lett. 9 6
[48]	Stoumpos C C, Kanatzidis M G 2015 Acc. Chem. Res 48 2791 Google Scholar
[49]	Savory C N, Walsh A, Scanlon D O 2016 ACS Energy Lett. 1 949 Google Scholar
[50]	Quan L N, García de Arquer F P, Sabatini R P, Sargent E H 2018 Adv. Mater. 30 1801996 Google Scholar
[51]	Heidari Gourji F, Velauthapillai D 2021 Molecules 26 2010 Google Scholar
[52]	Glazer A M 1972 Acta Crystallogr., Sect. B Struct. Crystallogr. Cryst. Chem. 28 3384 Google Scholar
[53]	Xie N, Zhang J, Raza S, Zhang N, Chen X, Wang D 2020 J. Phys.: Condens. Matter. 32 315901 Google Scholar
[54]	King-Smith R D, Vanderbilt D 1993 Phys. Rev. B 47 1651 Google Scholar
[55]	Resta R, Vanderbilt D 2007 Theory of Polarization: A Modern Approach (Berlin: Springer) p31
[56]	Schubert K, Fricke H 1951 Zeitschrift für Naturforschung A 6 781
[57]	Wdowik U D, Parlinski K, Rols S, Chatterji T 2014 Phys. Rev. B 89 224306 Google Scholar
[58]	Goldak J, Barrett C, Innes D, Youdelis W 1966 J. Chem. Phys. 44 3323 Google Scholar
[59]	Gonze X, Amadon B, Anglade P M, et al. 2009 Comput. Phys. Commun. 180 2582 Google Scholar
[60]	Ciucivara A, Sahu B R, Kleinman L 2006 Phys. Rev. B 73 214105 Google Scholar
[61]	Shaltaf R, Gonze X, Cardona M, Kremer R K, Siegle G 2009 Phys. Rev. B 79 075204 Google Scholar
[62]	Dangić D, Fahy S, Savić I 2022 Phys. Rev. B 106 134113 Google Scholar
[63]	Bechtel J S, Van der Ven A 2018 Phys. Rev. Mater. 2 025401 Google Scholar
[64]	Rabe K M, Joannopoulos J D 1987 Phys. Rev. B 36 6631 Google Scholar
[65]	Kooi B J, Wuttig M 2020 Adv. Mater. 32 1908302 Google Scholar
[66]	Ye Q J, Liu Z Y, Feng Y, Gao P, Li X Z 2018 Phys. Rev. Lett. 121 135702 Google Scholar
[67]	吕程烨, 陈英炜, 谢牧廷, 李雪阳, 于宏宇, 钟阳, 向红军 2023 72 237102 Google Scholar Lü C Y, Chen Y W, Xie M T, Li X Y, Yu H Y, Zhong Y, Xiang H J 2023 Acta Phys. Sin. 72 237102 Google Scholar
[68]	Zhang J L, Zhang F, Wei D N, Liu L, Liu X, Fang D, Zhang G X, Chen X, Wang D W 2022 Phys. Rev. B 105 094116 Google Scholar
[69]	Chang K, Liu J, Lin H, Wang N, Zhao K, Zhang A, Jin F, Zhong Y, Hu X, Duan W, Zhang Q, Fu L, Xue Q K, Chen X, Ji S H 2016 Science 353 274 Google Scholar
[70]	Wang B, Novendra N, Navrotsky A 2019 J. Am. Chem. Soc. 141 14501 Google Scholar
[71]	Gao L, Yadgarov L, Sharma R, Korobko R, McCall K M, Fabini D H, Stoumpos C C, Kanatzidis M G, Rappe A M, Yaffe O 2021 Mater. Adv. 2 4610 Google Scholar
[72]	Lee J H, Bristowe N C, Lee J H, Lee S H, Bristowe P D, Cheetham A K, Jang H M 2016 Chem. Mater. 28 4259 Google Scholar
[73]	Chen L, Xu B, Yang Y, Bellaiche L 2020 Adv. Funct. Mater. 30 1909496 Google Scholar
[74]	Jinnouchi R, Lahnsteiner J, Karsai F, Kresse G, Bokdam M 2019 Phys. Rev. Lett. 122 225701 Google Scholar
[75]	Bartók A P, Payne M C, Kondor R, Csányi G 2010 Phys. Rev. Lett. 104 136403 Google Scholar
[76]	Wang D W, Bokov A A, Ye Z G, Hlinka J, Bellaiche L 2016 Nat. Commun. 7 11014 Google Scholar
[77]	Wang D W, Liu L J, Liu J, Zhang N, Wei X Y 2018 Chin. Phys. B 27 127702 Google Scholar
[78]	Cohen A, Brenner T M, Klarbring J, Sharma R, Fabini D H, Korobko R, Nayak P K, Hellman O, Yaffe O 2022 Adv. Mater. 34 2107932 Google Scholar
[79]	Zhang L, Han J, Wang H, Car R, E W 2018 Phys. Rev. Lett. 120 143001 Google Scholar
[80]	Gu H Y, Yin W J, Gong X G 2021 Appl. Phys. Lett. 119 191101 Google Scholar
[81]	陈基, 冯页新, 李新征, 王恩哥 2015 64 183101 Google Scholar Chen J, Feng Y X, Li X Z, Wang E G 2015 Acta Phys. Sin. 64 183101 Google Scholar
[82]	Zhang Y, Sun J, Perdew J P, Wu X 2017 Phys. Rev. B 96 035143 Google Scholar
[83]	Wu Z, Cohen R E, Singh D J 2004 Phys. Rev. B 70 104112 Google Scholar
[84]	Yuk S F, Pitike K C, Nakhmanson S M, Eisenbach M, Li Y W, Cooper V R 2017 Sci. Rep. 7 43482 Google Scholar

[1]	宋睿, 刘雪梅, 王海滨, 吕皓, 宋晓艳. 机器学习辅助的WC-Co硬质合金硬度预测. , 2024, 73(12): 126201. doi: 10.7498/aps.73.20240284
[2]	张桥, 谭薇, 宁勇祺, 聂国政, 蔡孟秋, 王俊年, 朱慧平, 赵宇清. 基于机器学习和第一性原理计算的Janus材料的预测. , 2024, 73(23): 230201. doi: 10.7498/aps.73.20241278
[3]	张旭, 丁进敏, 侯晨阳, 赵一鸣, 刘鸿维, 梁生. 基于机器学习的激光匀光整形方法. , 2024, 73(16): 164205. doi: 10.7498/aps.73.20240747
[4]	张嘉晖. 蛋白质计算中的机器学习. , 2024, 73(6): 069301. doi: 10.7498/aps.73.20231618
[5]	刘烨, 牛赫然, 李兵兵, 马欣华, 崔树旺. 机器学习在宇宙线粒子鉴别中的应用. , 2023, 72(14): 140202. doi: 10.7498/aps.72.20230334
[6]	管星悦, 黄恒焱, 彭华祺, 刘彦航, 李文飞, 王炜. 生物分子模拟中的机器学习方法. , 2023, 72(24): 248708. doi: 10.7498/aps.72.20231624
[7]	罗启睿, 沈一凡, 罗孟波. 高分子塌缩相变和临界吸附相变的计算机模拟和机器学习. , 2023, 72(24): 240502. doi: 10.7498/aps.72.20231058
[8]	郭唯琛, 艾保全, 贺亮. 机器学习回归不确定性揭示自驱动活性粒子的群集相变. , 2023, 72(20): 200701. doi: 10.7498/aps.72.20230896
[9]	张嘉伟, 姚鸿博, 张远征, 蒋伟博, 吴永辉, 张亚菊, 敖天勇, 郑海务. 通过机器学习实现基于摩擦纳米发电机的自驱动智能传感及其应用. , 2022, 71(7): 078702. doi: 10.7498/aps.71.20211632
[10]	林键, 叶梦, 朱家纬, 李晓鹏. 机器学习辅助绝热量子算法设计. , 2021, 70(14): 140306. doi: 10.7498/aps.70.20210831
[11]	陈江芷, 杨晨温, 任捷. 基于波动与扩散物理系统的机器学习. , 2021, 70(14): 144204. doi: 10.7498/aps.70.20210879
[12]	王伟, 揭泉林. 基于机器学习J₁-J₂反铁磁海森伯自旋链相变点的识别方法. , 2021, 70(23): 230701. doi: 10.7498/aps.70.20210711
[13]	王鹏举, 范俊宇, 苏艳, 赵纪军. 基于机器学习构建的环三亚甲基三硝胺晶体势. , 2020, 69(23): 238702. doi: 10.7498/aps.69.20200690
[14]	杨自欣, 高章然, 孙晓帆, 蔡宏灵, 张凤鸣, 吴小山. 铅基钙钛矿铁电晶体高临界转变温度的机器学习研究. , 2019, 68(21): 210502. doi: 10.7498/aps.68.20190942
[15]	杨耀东. 铁电材料中发现等温相变. , 2016, 65(7): 070101. doi: 10.7498/aps.65.070101(R)
[16]	甘永超, 曹万强. 铁电相变中极化与介电性的随机场效应. , 2013, 62(12): 127701. doi: 10.7498/aps.62.127701
[17]	周耐根, 胡秋发, 许文祥, 李克, 周浪. 硅熔化特性的分子动力学模拟–-不同势函数的对比研究. , 2013, 62(14): 146401. doi: 10.7498/aps.62.146401
[18]	李会山, 李鹏程, 周效信. 强激光场中模型氢原子的势函数对产生高次谐波强度的影响. , 2009, 58(11): 7633-7639. doi: 10.7498/aps.58.7633
[19]	艾树涛, 蔡元贞. 与相变潜热有关的铁电-顺电相界动力学及其尺寸效应. , 2006, 55(7): 3721-3724. doi: 10.7498/aps.55.3721
[20]	艾树涛, 钟维烈, 王春雷, 王矜奉, 张沛霖. 铁电分子场与Onsager关系. , 2002, 51(8): 1739-1742. doi: 10.7498/aps.51.1739

计量

文章访问数: 2808
PDF下载量: 257
被引次数: 0

姓名
邮箱
手机号码
标题
留言内容
验证码

搜索

留言板

面向铁电相变的机器学习: 基于图卷积神经网络的分子动力学模拟