journal article·2022-09-29Open access

Improving Material Property Prediction by Leveraging the Large-Scale Computational Database and Deep Learning

Pin Chen, Jianwen Chen, Hui Yan, Qing Mo, Zexin Xu, Jinyu Liu, Wenqing Zhang, Yuedong Yang, Yutong Lu

The Journal of Physical Chemistry C· Volume 126· Issue 38

Abstract

Predicting physical and chemical properties of materials based on structures is critical for bottom-up material design. Many property prediction models and material training databases have been proposed, but accurately predicting properties is still challenging. Here, we report a package of “Matgen + CrystalNet” approach to improve material property prediction. We construct a large-scale material genome database (Matgen) containing 76k materials collected from an experimentally observed database and compute their properties through the density functional theory method with the Perdew–Burke–Ernzerhof (PBE) functional. Our database achieves the same computation accuracy by comparing part of our results with those from the open Material Project and Open Quantum Materials Database, all with PBE computations, and contains more diverse chemical species and big-sized structures. Based on the computed properties of our comprehensive data set, we have developed a new graph neural network (GNN) model, namely, CrystalNet, by strengthening the message passing between atoms and bonds to mimic physical and chemical interactions. The model is shown to outperform other GNN prediction models. The proof-of-concept applications, such as fine-tuning data on experimental values to improve prediction accuracy and bandgap prediction on hypothetical materials, showcase the usability and potential capacity of our package of “database + model” to improve material design.
Source: openalex_inverted_index · Quality: baseline

Research context

OpenAlex topics: Machine Learning in Materials Science · Computational Drug Discovery Methods · Surface Chemistry and Catalysis

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

Affiliations

National Supercomputer Center in Guangzhou, School of Computer Science and Engineering, Sun Yat-sen University, 132 East Circle at University City, Guangzhou 510006, China

Department of Materials Science and Engineering, and Shenzhen Institute for Quantum Science & Engineering, Southern University of Science and Technology, Shenzhen, Guangdong 518055, China

Guangdong Provincial Key Laboratory of Computational Science and Material Design, and Shenzhen Key Laboratory of Advanced Quantum Functional Materials and Devices, Southern University of Science and Technology, Shenzhen, Guangdong 518055, China

Funding

Guangdong Province Introduction of Innovative R&D Team · Guangdong Province

References (39)

Show source-provided references
1. 10.1038/s41563-019-0427-z10.1038/s41563-019-0427-z ↗
2. 10.1038/s43588-020-00006-710.1038/s43588-020-00006-7 ↗
3. 10.1038/s41563-021-01013-310.1038/s41563-021-01013-3 ↗
4. 10.1016/j.cej.2021.13041910.1016/j.cej.2021.130419 ↗
5. 10.1038/s41928-021-00599-510.1038/s41928-021-00599-5 ↗
6. 10.1038/s41560-020-00756-810.1038/s41560-020-00756-8 ↗
7. 10.1038/s41467-021-25135-z10.1038/s41467-021-25135-z ↗
8. 10.1103/PhysRev.140.A113310.1103/PhysRev.140.A1133 ↗
9. 10.1063/1.481232310.1063/1.4812323 ↗
10. 10.1107/S010876810200694810.1107/S0108768102006948 ↗
11. 10.1080/0889311041000166488210.1080/08893110410001664882 ↗
12. 10.1016/j.commatsci.2012.02.00210.1016/j.commatsci.2012.02.002 ↗
13. 10.1007/s11837-013-0755-410.1007/s11837-013-0755-4 ↗
14. 10.1038/sdata.2018.8210.1038/sdata.2018.82 ↗
15. 10.1557/mrs.2018.20810.1557/mrs.2018.208 ↗
16. 10.1007/s11431-019-9514-510.1007/s11431-019-9514-5 ↗
17. 10.1038/s41597-021-01022-610.1038/s41597-021-01022-6 ↗
18. 10.1103/PhysRevLett.120.14530110.1103/PhysRevLett.120.145301 ↗
19. 10.1063/1.501977910.1063/1.5019779 ↗
20. 10.1021/acs.chemmater.9b0129410.1021/acs.chemmater.9b01294 ↗
21. Gilmer J. · 2017 · 1263
22. 10.1107/S002188980901669010.1107/S0021889809016690 ↗
23. 10.1093/nar/gkr90010.1093/nar/gkr900 ↗
24. Song, Y.; Zheng, S.; Niu, Z.; Fu, Z.H.; Lu, Y.; Yang, Y. In Communicative Representation Learning on Attributed Molecular Graphs; IJCAI, 2020; pp 2831–2838.10.24963/ijcai.2020/392 ↗
25. 10.1063/1.494002610.1063/1.4940026 ↗
26. 10.1103/PhysRevB.54.1116910.1103/PhysRevB.54.11169 ↗
27. 10.1103/PhysRevLett.77.386510.1103/PhysRevLett.77.3865 ↗
28. 10.1103/PhysRevB.50.1795310.1103/PhysRevB.50.17953 ↗
29. 10.1103/PhysRevB.59.175810.1103/PhysRevB.59.1758 ↗
30. 10.1016/j.commatsci.2015.07.01910.1016/j.commatsci.2015.07.019 ↗
31. 10.1103/PhysRevB.13.518810.1103/PhysRevB.13.5188 ↗
32. 10.1103/PhysRevLett.51.59710.1103/PhysRevLett.51.597 ↗
33. 10.1103/PhysRevLett.105.19640310.1103/PhysRevLett.105.196403 ↗
34. 10.1016/j.commatsci.2011.02.02310.1016/j.commatsci.2011.02.023 ↗
35. 10.1186/s13321-020-0411-210.1186/s13321-020-0411-2 ↗
36. 10.1038/s43588-020-00002-x10.1038/s43588-020-00002-x ↗
37. 10.1038/s41467-019-13297-w10.1038/s41467-019-13297-w ↗
38. 10.1038/s41524-020-00352-010.1038/s41524-020-00352-0 ↗
39. 10.1021/acscentsci.0c0042610.1021/acscentsci.0c00426 ↗