journal article·2021Open access

High-efficient ab initio Bayesian active learning method and applications in prediction of two-dimensional functional materials

Xing-Yu Ma, Hou-Yi Lyu, Kuan-Rong Hao, Zhen-Gang Zhu, Qing-Bo Yan, Gang Su

Nanoscale· Volume 13· Issue 35

Abstract

Beyond the conventional trial-and-error method, machine learning offers a great opportunity to accelerate the discovery of functional materials, but still often suffers from difficulties such as limited materials data and the unbalanced distribution of target properties. Here, we propose the ab initio Bayesian active learning method that combines active learning and high-throughput ab initio calculations to accelerate the prediction of desired functional materials with ultrahigh efficiency and accuracy. We apply it as an instance to a large family (3119) of two-dimensional hexagonal binary compounds with unbalanced materials properties, and accurately screen out the materials with maximal electric polarization and proper photovoltaic band gaps, respectively, whereas the computational costs are significantly reduced by only calculating a few tenths of the possible candidates in comparison with a random search. This approach shows the enormous advantages for the cases with unbalanced distribution of target properties. It can be readily applied to seek a broad range of advanced materials.
Source: europepmc · Quality: candidate unverified · Source record ↗

Research context

OpenAlex topics: Machine Learning in Materials Science · Electronic and Structural Properties of Oxides · 2D Materials and Applications

SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.

Affiliations

School of Physical Sciences, University of Chinese Academy of Sciences, Beijing 100049, China

Center of Materials Science and Optoelectronics Engineering, College of Materials Science and Optoelectronic Technology, University of Chinese Academy of Sciences, Beijing 100049, China

School of Electronic, Electrical and Communication Engineering, University of Chinese Academy of Sciences, Beijing 100049, China

Kavli Institute for Theoretical Sciences, and CAS Center of Excellence in Topological Quantum Computation, University of Chinese Academy of Sciences, Beijing 100190, China

Funding

National Key Research and Development Program of China · Chinese Academy of Sciences · National Natural Science Foundation of China · Beijing Municipal Science and Technology Commission · Fundamental Research Funds for the Central Universities

References (72)

Show source-provided references
1. Kohn · Phys. Rev. · 1965 · 140 · A113310.1103/PhysRev.140.A1133 ↗
2. Curtarolo · Nat. Mater. · 2013 · 12 · 19110.1038/nmat3568 ↗
3. Jain · APL Mater. · 2013 · 1 · 01100210.1063/1.4812323 ↗
4. Mounet · Nat. Nanotechnol. · 2018 · 13 · 24610.1038/s41565-017-0035-5 ↗
5. Le · Chem. Rev. · 2012 · 112 · 288910.1021/cr200066h ↗
6. Panapitiya · J. Am. Chem. Soc. · 2018 · 140 · 1750810.1021/jacs.8b08800 ↗
7. Mazaheri · Phys. Rev. Mater. · 2019 · 3 · 06380210.1103/PhysRevMaterials.3.063802 ↗
8. Isayev · Nat. Commun. · 2017 · 8 · 1567910.1038/ncomms15679 ↗
9. Granda · Nature · 2018 · 559 · 37710.1038/s41586-018-0307-8 ↗
10. Severson · Nat. Energy · 2019 · 4 · 38310.1038/s41560-019-0356-8 ↗
11. Weng · Nat. Commun. · 2020 · 11 · 351310.1038/s41467-020-17263-9 ↗
12. Ma · J. Phys. Chem. Lett. · 2019 · 10 · 673410.1021/acs.jpclett.9b02420 ↗
13. Lu · Adv. Mater. · 2020 · 32 · 200265810.1002/adma.202002658 ↗
14. Sakurai · ACS Cent. Sci. · 2019 · 5 · 31910.1021/acscentsci.8b00802 ↗
15. Doan · Chem. Mater. · 2020 · 32 · 633810.1021/acs.chemmater.0c00768 ↗
16. Bassman · npj Comput. Mater. · 2018 · 4 · 7410.1038/s41524-018-0129-0 ↗
17. Gopakumar · Sci. Rep. · 2018 · 8 · 373810.1038/s41598-018-21936-3 ↗
18. Kusne · Nat. Commun. · 2020 · 11 · 596610.1038/s41467-020-19597-w ↗
19. Vandermause · npj Comput. Mater. · 2020 · 6 · 2010.1038/s41524-020-0283-z ↗
20. B.Settles , Active learning literature survey , University of Wisconsin-Madison Department of Computer Sciences , 2009
21. C. K. I.Williams and C. E.Rasmussen , in Advances in Neural Information Processing Systems 8 , ed. D. S. Touretzky , M. C. Mozer and M. E. Hasselmo , MIT Press , Cambridge, MA , 1996 , vol. 8 , pp. 514–520
22. Jones · J. Global Optim. · 1998 · 13 · 45510.1023/A:1008306431147 ↗
23. Choudhary · J. Phys.: Condens. Matter · 2020 · 32 · 475501
24. Zhang · Nat. Commun. · 2019 · 10 · 526010.1038/s41467-019-13214-1 ↗
25. Tran · Nat. Catal. · 2018 · 1 · 69610.1038/s41929-018-0142-1 ↗
26. Sheng · Phys. Rev. Lett. · 2011 · 106 · 15570310.1103/PhysRevLett.106.155703 ↗
27. Andrievski · Int. J. Refract. Met. Hard Mater. · 2001 · 19 · 44710.1016/S0263-4368(01)00023-3 ↗
28. Furthmüller · Phys. Rev. B: Condens. Matter Mater. Phys. · 1994 · 50 · 1560610.1103/PhysRevB.50.15606 ↗
29. Ding · Nat. Commun. · 2017 · 8 · 1495610.1038/ncomms14956 ↗
30. Wu · Nano Lett. · 2016 · 16 · 323610.1021/acs.nanolett.6b00726 ↗
31. Chang · Science · 2016 · 353 · 27410.1126/science.aad8609 ↗
32. Ma · Sci. Bull. · 2021 · 66 · 23310.1016/j.scib.2020.09.010 ↗
33. Ma · J. Phys. Chem. Lett. · 2021 · 12 · 97310.1021/acs.jpclett.0c03136 ↗
34. Hao · Nano Res. · 202110.1007/s12274-021-3415-6 ↗
35. Ghatge · Nat. Electron. · 2019 · 2 · 50610.1038/s41928-019-0305-3 ↗
36. Si · Nat. Electron. · 2019 · 2 · 58010.1038/s41928-019-0338-7 ↗
37. Wu · Nat. Electron. · 2020 · 3 · 46610.1038/s41928-020-0441-9 ↗
38. Dean · Nat. Nanotechnol. · 2010 · 5 · 72210.1038/nnano.2010.172 ↗
39. Ormaza · Nano Lett. · 2016 · 16 · 423010.1021/acs.nanolett.6b01197 ↗
40. Bekaert · Sci. Rep. · 2017 · 7 · 1445810.1038/s41598-017-13913-z ↗
41. Chanana · Phys. Rev. Lett. · 2019 · 123 · 03760110.1103/PhysRevLett.123.037601 ↗
42. Luo · Phys. Rev. B · 2017 · 96 · 23541510.1103/PhysRevB.96.235415 ↗
43. Xu · Phys. Chem. Chem. Phys. · 2020 · 22 · 169310.1039/C9CP05585A ↗
44. Que · J. Phys. Chem. Lett. · 2020 · 11 · 410710.1021/acs.jpclett.0c00981 ↗
45. Gou · Phys. Rev. Lett. · 2018 · 121 · 12680110.1103/PhysRevLett.121.126801 ↗
46. Tsai · Nature · 2016 · 536 · 31210.1038/nature18306 ↗
47. Li · Adv. Mater. · 2019 · 31 · 190196610.1002/adma.201901966 ↗
48. Miao · Nanoscale Horiz. · 2020 · 5 · 156610.1039/D0NH00395F ↗
49. Xie · Nano Energy · 2016 · 28 · 43310.1016/j.nanoen.2016.08.058 ↗
50. Das · Adv. Mater. · 2018 · 31 · 180272210.1002/adma.201802722 ↗
51. Anand · Nano Lett. · 2016 · 16 · 12610.1021/acs.nanolett.5b03275 ↗
52. Henry · J. Appl. Phys. · 1980 · 51 · 449410.1063/1.328272 ↗
53. Singh · Sol. Energy Mater. Sol. Cells · 2012 · 101 · 3610.1016/j.solmat.2012.02.019 ↗
54. Perdew · Phys. Rev. Lett. · 1996 · 77 · 386510.1103/PhysRevLett.77.3865 ↗
55. Dudarev · Phys. Rev. B: Condens. Matter Mater. Phys. · 1998 · 57 · 150510.1103/PhysRevB.57.1505 ↗
56. Friedman · Ann. Stat. · 2001 · 29 · 118910.1214/aos/1013203451 ↗
57. Heyd · J. Chem. Phys. · 2003 · 118 · 820710.1063/1.1564060 ↗
58. Herring · Phys. Rev. · 1956 · 101 · 94410.1103/PhysRev.101.944 ↗
59. Cheng · J. Am. Chem. Soc. · 2018 · 140 · 1789510.1021/jacs.8b07871 ↗
60. Cheng · Phys. Rev. Lett. · 2020 · 125 · 17770110.1103/PhysRevLett.125.177701 ↗
61. Cheng · J. Am. Chem. Soc. · 2019 · 141 · 1629610.1021/jacs.9b05923 ↗
62. Hedin · Phys. Rev. · 1965 · 139 · 79610.1103/PhysRev.139.A796 ↗
63. Strinati · Phys. Rev. B: Condens. Matter Mater. Phys. · 1984 · 29 · 571810.1103/PhysRevB.29.5718 ↗
64. Bishal · Results Phys. · 2018 · 11 · 3410.1016/j.rinp.2018.08.026 ↗
65. Fei · Phys. Rev. Lett. · 2016 · 117 · 09760110.1103/PhysRevLett.117.097601 ↗
66. Guan · Phys. Rev. B · 2018 · 97 · 14410410.1103/PhysRevB.97.144104 ↗
67. Cui · Nano Lett. · 2018 · 18 · 125310.1021/acs.nanolett.7b04852 ↗
68. Kresse · Phys. Rev. B: Condens. Matter Mater. Phys. · 1996 · 54 · 1116910.1103/PhysRevB.54.11169 ↗
69. Blöchl · Phys. Rev. B: Condens. Matter Mater. Phys. · 1994 · 50 · 1795310.1103/PhysRevB.50.17953 ↗
70. S.Maekawa , T.Tohyama , S. E.Barnes , S.Ishihara , W.Koshibae and G.Khaliullin , Physics of Transition Metal Oxides, Series in Solid State Sciences , Springer , Berlin Heidelberg , 2004 , vol. 144
71. You · Phys. Rev. Appl. · 2019 · 12 · 02406310.1103/PhysRevApplied.12.024063 ↗
72. Pedregosa · J. Mach. Learn. Res. · 2011 · 12 · 2825