Fundamental band gap and alignment of two-dimensional semiconductors explored by machine learning

doi:10.1088/1674-1056/ab75d5

中国物理B ›› 2020, Vol. 29 ›› Issue (4): 46101-046101.doi: 10.1088/1674-1056/ab75d5

• CONDENSED MATTER: STRUCTURAL, MECHANICAL, AND THERMAL PROPERTIES • 上一篇下一篇

Fundamental band gap and alignment of two-dimensional semiconductors explored by machine learning

Zhen Zhu(朱震), Baojuan Dong(董宝娟), Huaihong Guo(郭怀红), Teng Yang(杨腾), Zhidong Zhang(张志东)

1 Materials Department, University of California, Santa Barbara, CA 93106, USA;
2 Shenyang National Laboratory for Materials Science, Institute of Metal Research, Chinese Academy of Sciences, Shenyang 110016, China;
3 College of Sciences, Liaoning Shihua University, Fushun 113001, China;
4 State Key Laboratory of Quantum Optics and Quantum Optics Devices, Institute of Opto-Electronics, Shanxi University, Taiyuan 030006, China;
5 Collaborative Innovation Center of Extreme Optics, Shanxi University, Taiyuan 030006, China

收稿日期:2019-12-31 修回日期:2020-01-31 出版日期:2020-04-05 发布日期:2020-04-05
通讯作者: Zhen Zhu, Teng Yang E-mail:zhuzhen@engineering.ucsb.edu;yangteng@imr.ac.cn
基金资助:
This work is dedicated to Michelle Mucheng Zhu. Project supported by the National Key R&D Program of China (Grant No. 2017YFA0206301).

Fundamental band gap and alignment of two-dimensional semiconductors explored by machine learning

Zhen Zhu(朱震)¹, Baojuan Dong(董宝娟)^2,4,5, Huaihong Guo(郭怀红)³, Teng Yang(杨腾)², Zhidong Zhang(张志东)²

1 Materials Department, University of California, Santa Barbara, CA 93106, USA;
2 Shenyang National Laboratory for Materials Science, Institute of Metal Research, Chinese Academy of Sciences, Shenyang 110016, China;
3 College of Sciences, Liaoning Shihua University, Fushun 113001, China;
4 State Key Laboratory of Quantum Optics and Quantum Optics Devices, Institute of Opto-Electronics, Shanxi University, Taiyuan 030006, China;
5 Collaborative Innovation Center of Extreme Optics, Shanxi University, Taiyuan 030006, China

Received:2019-12-31 Revised:2020-01-31 Online:2020-04-05 Published:2020-04-05
Contact: Zhen Zhu, Teng Yang E-mail:zhuzhen@engineering.ucsb.edu;yangteng@imr.ac.cn
Supported by:
This work is dedicated to Michelle Mucheng Zhu. Project supported by the National Key R&D Program of China (Grant No. 2017YFA0206301).

摘要/Abstract

摘要： Two-dimensional (2D) semiconductors isoelectronic to phosphorene have been drawing much attention recently due to their promising applications for next-generation (opt)electronics. This family of 2D materials contains more than 400 members, including (a) elemental group-V materials, (b) binary III-VII and IV-VI compounds, (c) ternary III-VI-VII and IV-V-VII compounds, making materials design with targeted functionality unprecedentedly rich and extremely challenging. To shed light on rational functionality design with this family of materials, we systemically explore their fundamental band gaps and alignments using hybrid density functional theory (DFT) in combination with machine learning. First, calculations are performed using both the Perdew-Burke-Ernzerhof exchange-correlation functional within the general-gradient-density approximation (GGA-PBE) and Heyd-Scuseria-Ernzerhof hybrid functional (HSE) as a reference. We find this family of materials share similar crystalline structures, but possess largely distributed band-gap values ranging approximately from 0 eV to 8 eV. Then, we apply machine learning methods, including linear regression (LR), random forest regression (RFR), and support vector machine regression (SVR), to build models for the prediction of electronic properties. Among these models, SVR is found to have the best performance, yielding the root mean square error (RMSE) less than 0.15 eV for the predicted band gaps, valence-band maximums (VBMs), and conduction-band minimums (CBMs) when both PBE results and elemental information are used as features. Thus, we demonstrate that the machine learning models are universally suitable for screening 2D isoelectronic systems with targeted functionality, and especially valuable for the design of alloys and heterogeneous systems.

关键词: two-dimensional semiconductors, machine learning

Abstract: Two-dimensional (2D) semiconductors isoelectronic to phosphorene have been drawing much attention recently due to their promising applications for next-generation (opt)electronics. This family of 2D materials contains more than 400 members, including (a) elemental group-V materials, (b) binary III-VII and IV-VI compounds, (c) ternary III-VI-VII and IV-V-VII compounds, making materials design with targeted functionality unprecedentedly rich and extremely challenging. To shed light on rational functionality design with this family of materials, we systemically explore their fundamental band gaps and alignments using hybrid density functional theory (DFT) in combination with machine learning. First, calculations are performed using both the Perdew-Burke-Ernzerhof exchange-correlation functional within the general-gradient-density approximation (GGA-PBE) and Heyd-Scuseria-Ernzerhof hybrid functional (HSE) as a reference. We find this family of materials share similar crystalline structures, but possess largely distributed band-gap values ranging approximately from 0 eV to 8 eV. Then, we apply machine learning methods, including linear regression (LR), random forest regression (RFR), and support vector machine regression (SVR), to build models for the prediction of electronic properties. Among these models, SVR is found to have the best performance, yielding the root mean square error (RMSE) less than 0.15 eV for the predicted band gaps, valence-band maximums (VBMs), and conduction-band minimums (CBMs) when both PBE results and elemental information are used as features. Thus, we demonstrate that the machine learning models are universally suitable for screening 2D isoelectronic systems with targeted functionality, and especially valuable for the design of alloys and heterogeneous systems.

Key words: two-dimensional semiconductors, machine learning

中图分类号: (Elemental semiconductors)

73.61.Cw

61.46.-w (Structure of nanoscale materials) 73.22.-f (Electronic structure of nanoscale materials and related systems)

朱震, 董宝娟, 郭怀红, 杨腾, 张志东. Fundamental band gap and alignment of two-dimensional semiconductors explored by machine learning[J]. 中国物理B, 2020, 29(4): 46101-046101.

Zhen Zhu(朱震), Baojuan Dong(董宝娟), Huaihong Guo(郭怀红), Teng Yang(杨腾), Zhidong Zhang(张志东). Fundamental band gap and alignment of two-dimensional semiconductors explored by machine learning[J]. Chin. Phys. B, 2020, 29(4): 46101-046101.

参考文献 44

[1]	Novoselov K S, Geim A K, Morozov S V, Jiang D, Zhang Y, Dubonos S V, Grigorieva I V and Firsov A A 2004 Science 306 666 doi: 10.1126/science.1102896
[2]	Zhang Y, Tan Y W, Stormer H L and Kim P 2005 Nature 438 201 doi: 10.1038/nature04235
[3]	Mak K F and Shan J 2016 Nat. Photon. 10 216 doi: 10.1038/nphoton.2015.282
[4]	Fiori G, Bonaccorso F, Iannaccone G, Palacios T, Neumaier D, Seabaugh A, Banerjee S K and Colombo L 2014 Nat. Nanotechnol. 9 768 doi: 10.1038/nnano.2014.207
[5]	Radisavljevic B, Radenovic A, Brivio J, Giacometti I V and Kis A 2011 Nat. Nanotechnol. 6 147 doi: 10.1038/nnano.2010.279
[6]	Perera M M, Lin M W, Chuang H J, Chamlagain B P, Wang C, Tan X, Cheng M M C, Tománek D and Zhou Z 2013 ACS Nano 7 4449 doi: 10.1021/nn401053g
[7]	Li L, Yu Y, Ye G J, Ge Q, Ou X, Wu H, Feng D, Chen X H and Zhang Y 2014 Nat. Nanotechnol. 9 372 doi: 10.1038/nnano.2014.35
[8]	Liu H, Neal A T, Zhu Z, Luo Z, Xu X, Tománek D and Ye P D 2014 ACS Nano 8 4033 doi: 10.1021/nn501226z
[9]	Koenig S P, Doganov R A, Schmidt H, Castro Neto A H and Ozyilmaz B 2014 Appl. Phys. Lett. 104 103106 doi: 10.1063/1.4868132
[10]	Rodin A S, Carvalho A and Castro Neto A H 2014 Phys. Rev. Lett. 112 176801 doi: 10.1103/PhysRevLett.112.176801
[11]	Ling X, Wang H, Huang S, Xia F and Dresselhaus M S 2015 Proc. Natl. Acad. Sci. USA 112 4523 doi: 10.1073/pnas.1416581112
[12]	Liu H, Du Y, Deng Y and Peide D Y 2015 Chem. Soc. Rev. 44 2732 doi: 10.1039/C4CS00257A
[13]	Curtarolo S, Hart G L, Nardelli M B, Mingo N, Sanvito S and Levy O 2013 Nat. Mater. 12 191 doi: 10.1038/nmat3568
[14]	De Jong M, Chen W, Angsten T, et al. 2015 Scientific Data 2 150009 doi: 10.1038/sdata.2015.9
[15]	Setyawan W and Curtarolo S 2010 Computational Materials Science 49 299 doi: 10.1016/j.commatsci.2010.05.010
[16]	Hautier G, Jain A, Ong S P, Kang B, Moore C, Doe R and Ceder G 2011 Chemistry of Materials 23 3495 doi: 10.1021/cm200949v
[17]	https://icsd.fiz-karlsruhe.de
[18]	Ward L and Wolverton C 2017 Current Opinion in Solid State and Materials Science 21 167 doi: 10.1016/j.cossms.2016.07.002
[19]	Ward L, Agrawal A, Choudhary A and Wolverton C 2016 npj Computational Materials 2 16028 doi: 10.1038/npjcompumats.2016.28
[20]	Deml A M, O’Hayre R, Wolverton C and Stevanović V 2016 Phys. Rev. B 93 085142 doi: 10.1103/PhysRevB.93.085142
[21]	Pilania G, Gubernatis J E and Lookman T 2017 Computational Materials Science 129 156 doi: 10.1016/j.commatsci.2016.12.004
[22]	Lee J, Seko A, Shitara K, Nakayama K and Tanaka I 2016 Phys. Rev. B 93 115104 doi: 10.1103/PhysRevB.93.115104
[23]	Ramprasad R, Batra R, Pilania G, Mannodi-Kanakkithodi A and Kim C 2017 npj Computational Materials 3 54 doi: 10.1038/s41524-017-0056-5
[24]	Balachandran P V, Theiler J, Rondinelli J M and Lookman T 2015 Sci. Rep. 5 13285 doi: 10.1038/srep13285
[25]	Ji J, Song X, Liu J, et al. 2016 Nat. Commun. 7 13352 doi: 10.1038/ncomms13352
[26]	Zhang J L, Zhao S, Han C, et al. 2016 Nano Lett. 16 4903 doi: 10.1021/acs.nanolett.6b01459
[27]	Haleoot R, Paillard C, Mehboudi M, Xu B, Bellaiche L and BarrazaLopez S 2017 Phys. Rev. Lett. 118 227401 doi: 10.1103/PhysRevLett.118.227401
[28]	Fei R, Kang W and Yang L 2016 Phys. Rev. Lett. 117 097601 doi: 10.1103/PhysRevLett.117.097601
[29]	Blöchl P 1994 Phys. Rev. B 50 17953 doi: 10.1103/PhysRevB.50.17953
[30]	Kresse G and Furthmüller J 1996 Phys. Rev. B 54 11169 doi: 10.1103/PhysRevB.54.11169
[31]	Perdew J P, Burke K and Ernzerhof M 1996 Phys. Rev. Lett. 77 3865 doi: 10.1103/PhysRevLett.77.3865
[32]	Hestenes M R and Stiefel E 1952 J. Res. Natl. Bur. Stand. 49 409 doi: 10.6028/jres.049.044
[33]	Heyd J, Scuseria G E and Ernzerhof M 2003 J. Chem. Phys. 118 8207 doi: 10.1063/1.1564060
[34]	Heyd J, Scuseria G E and Ernzerhof M 2003 J. Chem. Phys. 124 219906
[35]	Monkhorst H J and Pack J D 1976 Phys. Rev. B 13 5188 doi: 10.1103/PhysRevB.13.5188
[36]	https://http://scikit-learn.org/
[37]	Zhu Z and Tománek D 2014 Phys. Rev. Lett. 112 176802 doi: 10.1103/PhysRevLett.112.176802
[38]	Zhang S, Yan Z, Li Y, Chen Z and Zeng H 2015 Angewandte Chemie 127 3155 doi: 10.1002/ange.201411246
[39]	Guan J, Zhu Z and Tománek D 2014 ACS Nano 8 12763 doi: 10.1021/nn5059248
[40]	Zhu Z, Guan J, Liu D and Tománek D 2015 ACS Nano 9 8284 doi: 10.1021/acsnano.5b02742
[41]	Wang J, Dong B J, Guo H, Yang T, Zhu Z, Hu G, Saito R and Zhang Z D 2017 Phys. Rev. B 95 045404 doi: 10.1103/PhysRevB.95.045404
[42]	Zhang Y, Guo H, Dong B J, Zhu Z, Yang T, Wang J and Zhang Z 2020 Chin. Phys. B 29 037305 doi: 10.1088/1674-1056/ab6c4e
[43]	Goodman C 1958 J. Phys. Chem. Solids 6 305 doi: 10.1016/0022-3697(58)90050-7
[44]	Matthews B E, Holder A M, Schelhas L, et al. 2017 J. Mater. Chem. A 5 16873 doi: 10.1039/C7TA03694A

Fundamental band gap and alignment of two-dimensional semiconductors explored by machine learning

Fundamental band gap and alignment of two-dimensional semiconductors explored by machine learning

RichHTML

PDF (PC)

赞

可视化

摘要/Abstract

引用本文

使用本文

参考文献 44

相关文章 15

Metrics

本文评价

推荐阅读 0

[1]	Jinlong Hu(胡锦龙), Yuting Zuo(左钰婷), Yuzhou Hao(郝昱州), Guoyu Shu(舒国钰), Yang Wang(王洋), Minxuan Feng(冯敏轩), Xuejie Li(李雪洁), Xiaoying Wang(王晓莹), Jun Sun(孙军), Xiangdong Ding(丁向东), Zhibin Gao(高志斌), Guimei Zhu(朱桂妹), Baowen Li(李保文). Prediction of lattice thermal conductivity with two-stage interpretable machine learning[J]. 中国物理B, 2023, 32(4): 46301-046301.
[2]	Xue-Yi Guo(郭学仪), Shang-Shu Li(李尚书), Xiao Xiao(效骁), Zhong-Cheng Xiang(相忠诚), Zi-Yong Ge(葛自勇), He-Kang Li(李贺康), Peng-Tao Song(宋鹏涛), Yi Peng(彭益), Zhan Wang(王战), Kai Xu(许凯), Pan Zhang(张潘), Lei Wang(王磊), Dong-Ning Zheng(郑东宁), and Heng Fan(范桁). Variational quantum simulation of thermal statistical states on a superconducting quantum processer[J]. 中国物理B, 2023, 32(1): 10307-010307.
[3]	Jing Yue(岳靖), Jian Li(李剑), Wen Zhang(张文), and Zhangxin Chen(陈掌星). The coupled deep neural networks for coupling of the Stokes and Darcy-Forchheimer problems[J]. 中国物理B, 2023, 32(1): 10201-010201.
[4]	Tonghe Ying(应通和), Jianbao Zhu(朱健保), and Wenguang Zhu(朱文光). Machine learning potential aided structure search for low-lying candidates of Au clusters[J]. 中国物理B, 2022, 31(7): 78402-078402.
[5]	Yong Huang(黄勇) and Yang Li(李扬). Data-driven modeling of a four-dimensional stochastic projectile system[J]. 中国物理B, 2022, 31(7): 70501-070501.
[6]	Shi-Jie Pan(潘世杰), Lin-Chun Wan(万林春), Hai-Ling Liu(刘海玲), Yu-Sen Wu(吴宇森), Su-Juan Qin(秦素娟), Qiao-Yan Wen(温巧燕), and Fei Gao(高飞). Quantum algorithm for neighborhood preserving embedding[J]. 中国物理B, 2022, 31(6): 60304-060304.
[7]	Ruoting Zhao(赵若廷), Bangyu Xing(邢邦昱), Huimin Mu(穆慧敏), Yuhao Fu(付钰豪), and Lijun Zhang(张立军). Evaluation of performance of machine learning methods in mining structure—property data of halide perovskite materials[J]. 中国物理B, 2022, 31(5): 56302-056302.
[8]	Yan-Yan Hou(侯艳艳), Jian Li(李剑), Xiu-Bo Chen(陈秀波), and Yuan Tian(田源). Quantum partial least squares regression algorithm for multiple correlation problem[J]. 中国物理B, 2022, 31(3): 30304-030304.
[9]	Jintao Yang(杨锦涛), Junpeng Cao(曹俊鹏), and Wen-Li Yang(杨文力). Dynamical learning of non-Markovian quantum dynamics[J]. 中国物理B, 2022, 31(1): 10314-010314.
[10]	Yicheng Wu(吴义成), Bin Xu(徐斌), Yitao Sun(孙奕韬), and Pengfei Guan(管鹏飞). Quantitative structure-plasticity relationship in metallic glass: A machine learning study[J]. 中国物理B, 2021, 30(5): 57103-057103.
[11]	Yuansheng Chen(陈元盛) and Fei Tong(仝飞). Stability analysis of hydro-turbine governing system based on machine learning[J]. 中国物理B, 2021, 30(12): 120509-120509.
[12]	M R C Mahdy, Hamim Mahmud Rivy, Ziaur Rahman Jony, Nabila Binte Alam, Nabila Masud, Golam Dastegir Al Quaderi, Ibraheem Muhammad Moosa, Chowdhury Mofizur Rahman, M Sohel Rahman. Dielectric or plasmonic Mie object at air-liquid interface: The transferred and the traveling momenta of photon[J]. 中国物理B, 2020, 29(1): 14211-014211.
[13]	张博, 郑新奇, 赵同云, 胡凤霞, 孙继荣, 沈保根. Machine learning technique for prediction of magnetocaloric effect in La(Fe, Si/Al)₁₃-based materials[J]. 中国物理B, 2018, 27(6): 67503-067503.
[14]	李锐, 刘瑶, 左淑兰, 赵同云, 胡凤霞, 孙继荣, 沈保根. Composition design for (PrNd-La–Ce)₂Fe₁₄B melt-spun magnets by machine learning technique[J]. 中国物理B, 2018, 27(4): 47501-047501.
[15]	辛涛, 王碧雪, 李可仁, 孔祥宇, 魏世杰, 王涛, 阮东, 龙桂鲁. Nuclear magnetic resonance for quantum computing: Techniques and recent achievements[J]. 中国物理B, 2018, 27(2): 20308-020308.