journal article·2021-10Open access

High‐Throughput Discovery of Novel Cubic Crystal Materials Using Deep Generative Neural Networks

Yong Zhao, Mohammed Al‐Fahdi, Ming Hu, Edirisuriya M. D. Siriwardane, Yuqi Song, Alireza Nasiri, Jianjun Hu

Advanced Science· Volume 8· Issue 20

Abstract

Abstract High‐throughput screening has become one of the major strategies for the discovery of novel functional materials. However, its effectiveness is severely limited by the lack of sufficient and diverse materials in current materials repositories such as the open quantum materials database (OQMD). Recent progress in deep learning have enabled generative strategies that learn implicit chemical rules for creating hypothetical materials with new compositions and structures. However, current materials generative models have difficulty in generating structurally diverse, chemically valid, and stable materials. Here we propose CubicGAN, a generative adversarial network (GAN) based deep neural network model for large scale generative design of novel cubic materials. When trained on 375 749 ternary materials from the OQMD database, the authors show that the model is able to not only rediscover most of the currently known cubic materials but also generate hypothetical materials of new structure prototypes. A total of 506 such materials have been verified by phonon dispersion calculation. Considering the importance of cubic materials in wide applications such as solar panels, the GAN model provides a promising approach to significantly expand existing materials repositories, enabling the discovery of new functional materials via screening. The new crystal structures discovered are freely accessible at www.carolinamatdb.org.
Source: crossref · Quality: baseline

Research context

OpenAlex topics: Machine Learning in Materials Science · X-ray Diffraction in Crystallography · Topic Modeling

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

Affiliations

Department of Computer Science and Engineering University of South Carolina Columbia SC 29201 USA

Department of Mechanical Engineering University of South Carolina Columbia SC 29201 USA

Funding

National Science Foundation

References (60)

Show source-provided references
1. 10.1039/c1cc10674k10.1039/c1cc10674k ↗
2. 10.1039/C6EE02697D10.1039/C6EE02697D ↗
3. 10.1103/PhysRevMaterials.2.12380110.1103/PhysRevMaterials.2.123801 ↗
4. 10.1038/s41524-020-00375-710.1038/s41524-020-00375-7 ↗
5. 10.1002/aenm.20200235610.1002/aenm.202002356 ↗
6. 10.1016/j.joule.2018.08.01710.1016/j.joule.2018.08.017 ↗
7. 10.1107/S010876810200694810.1107/S0108768102006948 ↗
8. A. R.Oganov L.Andriy V.Mario F.Gilles inCECAM‐Workshop Lausanne2012 pp.22–26.
9. 10.1038/s41578-019-0101-810.1038/s41578-019-0101-8 ↗
10. 10.1103/PhysRevB.82.09411610.1103/PhysRevB.82.094116 ↗
11. 10.1016/j.cpc.2006.07.02010.1016/j.cpc.2006.07.020 ↗
12. 10.1038/s41524-020-00352-010.1038/s41524-020-00352-0 ↗
13. T.Long N. M.Fortunato I.Opahle Y.Zhang I.Samathrakis C.Shen O.Gutfleisch H.Zhang arXiv:2007.112282020.
14. Z.Ren J.Noh S.Tian F.Oviedo G.Xing Q.Liang A.Aberle Y.Liu Q.Li S.Jayavelu K.Hippalgaonkar Y.Jung T.Buonassisi arXiv:2005.076092020.
15. 10.1016/j.matt.2019.08.01710.1016/j.matt.2019.08.017 ↗
16. S.Kim J.Noh G. H.Gu A.Aspuru‐Guzik Y.Jung arXiv:2004.013962020.
17. 10.1021/ic102031h10.1021/ic102031h ↗
18. 10.1038/s41524-020-00422-310.1038/s41524-020-00422-3 ↗
19. Y.Song E. M. D.Siriwardane Y.Zhao J.Hu arXiv:2012.093142020.
20. 10.1039/D0SC00594K10.1039/D0SC00594K ↗
21. Jung Y. · 2018
22. 10.1038/324046a010.1038/324046a0 ↗
23. 10.1021/jp970984n10.1021/jp970984n ↗
24. 10.1063/1.172481610.1063/1.1724816 ↗
25. A.Nouira N.Sokolovska J.‐C.Crivello arXiv:1810.11203 2018.
26. 10.1021/acs.jcim.0c0046410.1021/acs.jcim.0c00464 ↗
27. 10.1039/D0MH00881H10.1039/D0MH00881H ↗
28. 10.1126/science.112764710.1126/science.1127647 ↗
29. D. P.Kingma M.Welling arXiv:1312.61142013.
30. C.Doersch arXiv:1606.059082016.
31. M.Arjovsky S.Chintala L.Bottou arXiv:1701.07875 2017.
32. Zhu J.‐Y. · 2017 · 2223
33. 10.1038/npjcompumats.2015.1010.1038/npjcompumats.2015.10 ↗
34. 10.1063/1.481232310.1063/1.4812323 ↗
35. 10.1007/s11837-013-0755-410.1007/s11837-013-0755-4 ↗
36. 10.1103/PhysRevLett.120.14530110.1103/PhysRevLett.120.145301 ↗
37. 10.1021/acs.chemmater.9b0129410.1021/acs.chemmater.9b01294 ↗
38. 10.1073/pnas.180118111510.1073/pnas.1801181115 ↗
39. 10.1038/s41586-019-1335-810.1038/s41586-019-1335-8 ↗
40. M.Mirza S.Osindero arXiv:1411.17842014.
41. Goodfellow I. · Adv. Nueral Inf. Process. Syst. · 2014 · 2672
42. Gulrajani I. · Adv. Neural Inf. Process. Syst. · 2017 · 5767
43. Y.Li W.Yang R.Dong J.Hu arXiv:2010.160992020.
44. Abadi M. · 2016 · 265
45. F.Chollet et al. Keras https://keras.io2015. Last accessed on October 2020.
46. 10.1126/science.aat266310.1126/science.aat2663 ↗
47. 10.1016/j.commatsci.2012.10.02810.1016/j.commatsci.2012.10.028 ↗
48. 10.1103/PhysRevB.65.10410410.1103/PhysRevB.65.104104 ↗
49. 10.1016/j.cpc.2017.07.02010.1016/j.cpc.2017.07.020 ↗
50. 10.1016/j.scriptamat.2015.07.02110.1016/j.scriptamat.2015.07.021 ↗
51. 10.1016/j.commatsci.2016.10.01510.1016/j.commatsci.2016.10.015 ↗
52. Chung S. · 2014 · 012002
53. B.Thapa M.Dubajic M. P.Nielsen R.Patterson G.Conibeer S.Shrestha in2020 47th IEEE Photovoltaic Specialists Conference (PVSC) Piscataway NJ2020pp. 0793–0797.10.1109/PVSC45281.2020.9300430 ↗
54. 10.1103/PhysRevB.99.12514110.1103/PhysRevB.99.125141 ↗
55. 10.1038/ncomms1175510.1038/ncomms11755 ↗
56. 10.1039/C8CP05455J10.1039/C8CP05455J ↗
57. 10.1039/C8CP03982H10.1039/C8CP03982H ↗
58. 10.1016/j.ijheatmasstransfer.2020.11948110.1016/j.ijheatmasstransfer.2020.119481 ↗
59. 10.1103/PhysRevB.95.19541610.1103/PhysRevB.95.195416 ↗
60. Maaten L. v. d. · J. Mach. Learn. Res. · 2008 · 9 · 2579