journal article·2018-12-31Open access

A general representation scheme for crystalline solids based on Voronoi-tessellation real feature values and atomic property data

Randy Jalem, Masanobu Nakayama, Yusuke Noda, Tam Le, Ichiro Takeuchi, Yoshitaka Tateyama, Hisatsugu Yamazaki

Abstract

Increasing attention has been paid to materials informatics approaches that promise efficient and fast discovery and optimization of functional inorganic materials. Technical breakthrough is urgently requested to advance this field and efforts have been made in the development of materials descriptors to encode or represent characteristics of crystalline solids, such as chemical composition, crystal structure, electronic structure, etc. We propose a general representation scheme for crystalline solids that lifts restrictions on atom ordering, cell periodicity, and system cell size based on structural descriptors of directly binned Voronoi-tessellation real feature values and atomic/chemical descriptors based on the electronegativity of elements in the crystal. Comparison was made vs. radial distribution function (RDF) feature vector, in terms of predictive accuracy on density functional theory (DFT) material properties: cohesive energy (CE), density (d), electronic band gap (BG), and decomposition energy (Ed). It was confirmed that the proposed feature vector from Voronoi real value binning generally outperforms the RDF-based one for the prediction of aforementioned properties. Together with electronegativity-based features, Voronoi-tessellation features from a given crystal structure that are derived from second-nearest neighbor information contribute significantly towards prediction.
Source: europepmc · Quality: candidate unverified · Source record ↗

Research context

OpenAlex topics: Machine Learning in Materials Science · X-ray Diffraction in Crystallography · Computational Drug Discovery Methods

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

Affiliations

Japan Science and Technology Agency (JST), PRESTO , Saitama, Japan

National Institute for Materials Science – Global Research Center for Environment and Energy Based on Nanomaterials Science (NIMS – GREEN) , Tsukuba, Japan

Center for Materials Research by Information Integration (CMI2), Research and Services Division of Materials Data and Integrated System (MaDIS), National Institute for Materials Science – ‘Materials Research by Information Integration’ Initiative (NIMS – Mi2i) , Tsukuba, Japan

Frontier Research Institute for Materials Science, Nagoya Institute of Technology , Nagoya, Japan

Elements Strategy Initiative for Catalysts and Batteries, Kyoto University , Kyoto, Japan

Department of Computer Science, Nagoya Institute of Technology , Nagoya, Japan

RIKEN Center for Advanced Intelligence Project , Tokyo, Japan

Battery Material Engineering & Research Division, Toyota Motor Corporation , Susono, Japan

Funding

Information Integration’ Initiative (MI2I); the Development Program of the Japan Science · Technology Agency (JST) under ‘Advanced Materials Informatics through Comprehensive Integration among Theoretical, Experimental, Computational · Data-centric Sciences’ research · ‘Elements Strategy Initiative to Form Core Research Center’ (Since 2012); Ministry of Education Culture, Sports, Science · Technology (MEXT); JST Precursory Research for Embryonic Science · Technology (PRESTO) program for the financial support · Materials research by Information Integration’ Initiative · the Development Program of the Japan Science and Technology Agency · Ministry of Education Culture, Sports, Science and Technology · JST Precursory Research for Embryonic Science and Technology

References (58)

Show source-provided references
1. 10.1016/j.commatsci.2011.02.02310.1016/j.commatsci.2011.02.023 ↗
2. 10.1007/s11837-013-0755-410.1007/s11837-013-0755-4 ↗
3. 10.1016/j.commatsci.2014.05.01410.1016/j.commatsci.2014.05.014 ↗
4. 10.1021/jz502319n10.1021/jz502319n ↗
5. 10.1002/aenm.v3.810.1002/aenm.v3.8 ↗
6. 10.1039/C5EE00685F10.1039/C5EE00685F ↗
7. Hautier G · Aip Conf Proc · 2016 · 1765 · 020009(1–10)
8. 10.1021/ci500752n10.1021/ci500752n ↗
9. 10.1038/ncomms555310.1038/ncomms5553 ↗
10. 10.1038/nchem.220710.1038/nchem.2207 ↗
11. 10.1088/0957-0233/16/1/03510.1088/0957-0233/16/1/035 ↗
12. 10.1021/acs.jpclett.5b0166010.1021/acs.jpclett.5b01660 ↗
13. 10.1021/acscombsci.5b0017810.1021/acscombsci.5b00178 ↗
14. 10.1103/PhysRevLett.115.20590110.1103/PhysRevLett.115.205901 ↗
15. 10.1016/j.commatsci.2013.10.01610.1016/j.commatsci.2013.10.016 ↗
16. 10.1021/cm503507 h10.1021/cm503507 h ↗
17. 10.1126/sciadv.160224110.1126/sciadv.1602241 ↗
18. 10.1103/PhysRevLett.114.10550310.1103/PhysRevLett.114.105503 ↗
19. 10.1021/cm300042710.1021/cm3000427 ↗
20. 10.1039/C3TA13235H10.1039/C3TA13235H ↗
21. 10.1038/srep3425610.1038/srep34256 ↗
22. 10.1103/PhysRevB.89.09410410.1103/PhysRevB.89.094104 ↗
23. Janežič D · 2007
24. 10.1021/ct400195d10.1021/ct400195d ↗
25. 10.1103/PhysRevLett.108.05830110.1103/PhysRevLett.108.058301 ↗
26. 10.1103/PhysRevB.89.20511810.1103/PhysRevB.89.205118 ↗
27. 10.1103/PhysRevB.95.14411010.1103/PhysRevB.95.144110 ↗
28. 10.1126/sciadv.170181610.1126/sciadv.1701816 ↗
29. 10.1103/PhysRevLett.104.13640310.1103/PhysRevLett.104.136403 ↗
30. 10.1515/crll.1908.134.19810.1515/crll.1908.134.198 ↗
31. Voronoi G · J Reine Angew Math · 1909 · 136 · 6710.1515/crll.1909.136.67 ↗
32. 10.1103/PhysRevB.90.05410210.1103/PhysRevB.90.054102 ↗
33. 10.1038/ncomms1567910.1038/ncomms15679 ↗
34. 10.1103/PhysRevB.54.1116910.1103/PhysRevB.54.11169 ↗
35. 10.1103/PhysRevB.59.175810.1103/PhysRevB.59.1758 ↗
36. 10.1103/PhysRevB.79.15510710.1103/PhysRevB.79.155107 ↗
37. ICSD, Inorganic Crystal Structure Database . 2006. Available from: http://icsd.fizkarlsruhe.de/icsd/.
38. 10.1103/RevModPhys.64.104510.1103/RevModPhys.64.1045 ↗
39. 10.1103/PhysRevB.52.R546710.1103/PhysRevB.52.R5467 ↗
40. 10.1103/PhysRevB.57.150510.1103/PhysRevB.57.1505 ↗
41. 10.1103/PhysRev.139.A79610.1103/PhysRev.139.A796 ↗
42. 10.1016/S0081-1947(08)60248-910.1016/S0081-1947(08)60248-9 ↗
43. 10.1021/ja01348a01110.1021/ja01348a011 ↗
44. 10.1107/S056773947600155110.1107/S0567739476001551 ↗
45. 10.1016/0031-3203(71)90013-610.1016/0031-3203(71)90013-6 ↗
46. 10.1107/S056773947900176510.1107/S0567739479001765 ↗
47. 10.1021/cm970361 m10.1021/cm970361 m ↗
48. 10.1063/1.321572210.1063/1.3215722 ↗
49. 10.1021/acs.jctc.7b0057710.1021/acs.jctc.7b00577 ↗
50. 10.1214/aos/101320345110.1214/aos/1013203451 ↗
51. 10.1023/B:STCO.0000035301.49549.8810.1023/B:STCO.0000035301.49549.88 ↗
52. Pedregosa F · J Mach Learn Res · 2011 · 12 · 2825
53. 10.1162/neco.1994.6.5.85110.1162/neco.1994.6.5.851 ↗
54. 10.1021/acs.jpcc.7b0742110.1021/acs.jpcc.7b07421 ↗
55. 10.1103/PhysRevB.57.1344810.1103/PhysRevB.57.13448 ↗
56. 10.1107/S002188980801201610.1107/S0021889808012016 ↗
57. Persistence of Vision Raytracer . Version 3.6. [Computer software]. Persistence of Vision Pty; 2004. Available from: http://www.povray.org/download/.
58. 10.1109/MCSE.2007.5510.1109/MCSE.2007.55 ↗