Study on bandgap predications of ABX3-type perovskites by machine learning
Source abstract
Abstract
The accurate bandgap prediction of perovskites has great significance for solar cell devices. Although density functional theory can be used for the calculations of material bandgaps, this method requires rich material calculation knowledge, and there are often some questions about whether the results are consistent with actual experimental results or not. To address this, the present work adopts machine learning (ML) to predict bandgaps of perovskites, where we collect 227 sets of experimental bandgap data of perovskites from the latest 1254 publications, to establish and identify 4 models from 24 kinds of ML models. The results of the models achieve high accuracy with root mean square error (RMSE) of down to 0.55 and meanwhile, the pearson correlation coefficient of up to 99%. In addition, our ML models give the effect of each chemical composition constituting the ABX 3 -type perovskites on the bandgaps by using the SHAP value, and they can be well explained in physics. These results all show the powerful potential of machine learning to fast and accurately predicate the bandgaps of perovskite for solar cell devices.
Source: expertdata · Quality: candidate unverified · Source record ↗
Research context
OpenAlex topics: Perovskite Materials and Applications · Chalcogenide Semiconductor Thin Films · Quantum Dots Synthesis And Properties
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (45)
Show source-provided references
1. Yang · Science · 2017 · 356 · 137610.1126/science.aan2301 ↗
2. Sharma · Nat. Commun. · 2014 · 5 · 484510.1038/ncomms5845 ↗
3. Meng · Nat. Commun. · 2018 · 9 · 526510.1038/s41467-018-07255-1 ↗
4. Jung · Nature · 2019 · 567 · 51110.1038/s41586-019-1036-3 ↗
5. Gao · Adv. Mater. · 2020 · 32
6. Lim · Energy Environ. Sci. · 2016 · 9 · 93210.1039/C5EE03560K ↗
7. Jeon · Nat. Energy · 2018 · 3 · 68210.1038/s41560-018-0200-6 ↗
8. Bakr · Nano Energy · 2017 · 34 · 27110.1016/j.nanoen.2017.02.025 ↗
9. Calio · Angew. Chem. Int. Ed. · 2016 · 55 · 1452210.1002/anie.201601757 ↗
10. Shockley · J. Appl. Phys. · 1961 · 32 · 510.z10.1063/1.1736034 ↗
11. Hossain · Nano-Micro Lett. · 2019 · 11 · 5810.1007/s40820-019-0287-8 ↗
12. Hu · Nano Energy · 2020 · 68 · 10436210.1016/j.nanoen.2019.104362 ↗
13. Kim · Sci. Data · 2017 · 4 · 17005710.1038/sdata.2017.57 ↗
14. Castelli · Apl. Mater. · 2014 · 210.1063/1.4893495 ↗
15. Jordan · Science · 2015 · 349 · 25510.1126/science.aaa8415 ↗
16. Wang · MRS. Commun. · 2019 · 9 · 79310.1557/mrc.2019.85 ↗
17. Schmidt · Science · 2009 · 324 · 8110.1126/science.1165893 ↗
18. Davies · Chem. Mater. · 2019 · 31 · 722110.1021/acs.chemmater.9b01519 ↗
19. Xue · Nat. Commun. · 2016 · 7 · 1124110.1038/ncomms11241 ↗
20. Xue · Proc. Nat. Acad. Sci.USA · 2016 · 113 · 1330110.1073/pnas.1607412113 ↗
21. Odabasi · Sol. Energy. Mater. Cell. · 2019 · 205 · 11028410.1016/j.solmat.2019.110284 ↗
22. Lu · Nat. Commun. · 2018 · 9 · 340510.1038/s41467-018-05761-w ↗
23. Weng · Nat. Commun. · 2020 · 11 · 351310.1038/s41467-020-17263-9 ↗
24. Pilania · Sci. Rep. · 2016 · 6 · 1937510.1038/srep19375 ↗
25. Zheng · J. Chinese. Nonfer. Metal. · 2018 · 29 · 803
26. Lundberg · Adv. Neu Inform. Process. · 2017 · 30 · 4765
27. Even · Phys. Status Solidi R. · 2014 · 8 · 3110.1002/pssr.201308183 ↗
28. Meloni · J. Mater. Chem. · 2016 · 4 · 1599710.1039/C6TA04949D ↗
29. Padmavathy · Electron. Mater. · 2019 · 48 · 124310.1007/s11664-018-06850-8 ↗
30. Xiao · J. Eur. Chemistry.A. · 2018 · 24 · 230510.1002/chem.201705031 ↗
31. Umebayashi · Phys. Rev. B · 2003 · 67 · 15540510.1103/PhysRevB.67.155405 ↗
32. Gao · Energy Environ. Sci. · 2014 · 710.1039/C4EE00942H ↗
33. Brivio · Apl. Mater. · 2013 · 110.1063/1.4824147 ↗
34. Chang · J. Kor. Phys. Soc. · 2004 · 44 · 88910.3938/jkps.44.638 ↗
35. Knutson · Inorg. Chem. · 2005 · 4410.1021/ic050244q ↗
36. Noel · Energy Environ. Sci. · 2014 · 710.1039/C4EE01076K ↗
37. Noh · Nano Lett. · 2013 · 13 · 176410.1021/nl400349b ↗
38. Eperon · Energy Environ. Sci. · 2014 · 7 · 98210.1039/c3ee43822h ↗
39. Im · J.Phy .Chem. Letters · 2015 · 6 · 350310.1021/acs.jpclett.5b01738 ↗
40. Hao · J. Am. Chem. Soc. · 2014 · 136 · 809410.1021/ja5033259 ↗
41. Lin · Phys. Status Solidi R. · 2021 · 12
42. Atourki · J. Alloys Compd. · 2017 · 702 · 40410.1016/j.jallcom.2017.01.205 ↗
43. Ghaithan · J. Phys. Chem. C · 2021 · 125 · 88610.1021/acs.jpcc.0c07983 ↗
44. Kang · J. Phys. Chem. Lett. · 2018 · 9 · 83010.1021/acs.jpclett.7b03333 ↗
45. Paul · J. Mater. Chem. C · 2018 · 6 · 332210.1039/C7TC05703B ↗