journal article·2023-08-31

Machine Learning Combined with Weighted Voting Regression and Proactive Searching Progress to Discover ABO3-δ Perovskites with High Oxide Ionic Conductivity

Pengcheng Xu, Tian Lu, Xiaobo Ji, Minjie Li, Wencong Lu

The Journal of Physical Chemistry C· Volume 127· Issue 34
Publisher page

Abstract

ABO 3-δ -type perovskites are one of the important oxygen ion conductors because of the enhanced properties through adjustments to the composition via elemental doping. In this work, machine learning combined with weighted voting regression (WVR) and proactive searching progress (PSP) was used to develop a model with high accuracy for the prediction of the oxide ionic conductivity of doped ABO 3-δ perovskites. After feature selection, algorithm selection, and parameter optimization, Gradient Boosting regression (GBR), random forest regression (RFR), and extra trees regression (ETR) were determined to be the optimal methods for WVR in constructing the integrated model. The R values of leave-one-out cross-validation (LOOCV) and the test set for the integrated model M WVR could reach 0.812 and 0.920, respectively. After the PSP was conducted, a total of 179 perovskites with high oxide ionic conductivity were discovered. PSP searching identified 8 types of perovskites with high oxide ionic conductivity. Pattern recognition was employed to identify the optimization area that exhibited a high oxide ionic conductivity. Visualization of factor effects was used to visualize the effect of the doping element type and ratio on the oxide ionic conductivity. The Shapley Additive exPlanations (SHAP) analysis of the significant features revealed that R a /R b had the highest influence on the oxide ionic conductivity with a negative impact. The developed integrated model, explored patterns, and optimization areas in this work can serve as a valuable guide for the discovery and design of perovskites with high oxide ionic conductivity.
Source: openalex_inverted_index · Quality: baseline

Research context

OpenAlex topics: Machine Learning in Materials Science · Advancements in Solid Oxide Fuel Cells · Advanced Photocatalysis Techniques

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

Affiliations

Materials Genome Institute, Shanghai University, Shanghai 200444, China

Shanghai Shuzhiwei Information Technology Co., LTD., 668 ShangDa Road, Shanghai 200444, China

Department of Chemistry, College of Sciences, Shanghai University, Shanghai 200444, China

Zhejiang Laboratory, Hangzhou 311100, China

Key Laboratory of Silicate Cultural Relics Conservation (Shanghai University), Ministry of Education, Shanghai 200444, China

Funding

Shanghai Municipal Education Commission · National Natural Science Foundation of China · Yunnan Precious Metals Laboratory Co., Ltd

References (52)

Show source-provided references
1. 10.1039/D2CC05288A10.1039/D2CC05288A ↗
2. 10.1016/j.ijhydene.2011.09.08410.1016/j.ijhydene.2011.09.084 ↗
3. 10.1016/j.snb.2019.12752110.1016/j.snb.2019.127521 ↗
4. 10.1039/b704426g10.1039/b704426g ↗
5. 10.2109/jcersj2.117.105510.2109/jcersj2.117.1055 ↗
6. 10.1016/j.ssi.2016.09.00710.1016/j.ssi.2016.09.007 ↗
7. 10.1680/jnaen.18.0000410.1680/jnaen.18.00004 ↗
8. 10.1016/j.ijhydene.2009.11.09210.1016/j.ijhydene.2009.11.092 ↗
9. 10.1038/s41586-021-03264-110.1038/s41586-021-03264-1 ↗
10. 10.1016/S0167-2738(00)00424-010.1016/S0167-2738(00)00424-0 ↗
11. 10.1002/inf2.1202810.1002/inf2.12028 ↗
12. 10.1038/s41586-018-0337-210.1038/s41586-018-0337-2 ↗
13. Zang X. · Molecules · 2022 · 2810.3390/molecules28010322 ↗
14. 10.1021/acspolymersau.2c0005310.1021/acspolymersau.2c00053 ↗
15. 10.1021/acs.jpclett.2c0307310.1021/acs.jpclett.2c03073 ↗
16. 10.1016/j.commatsci.2021.11052810.1016/j.commatsci.2021.110528 ↗
17. 10.1021/acs.jpclett.1c0193910.1021/acs.jpclett.1c01939 ↗
18. 10.1021/acsami.2c0056410.1021/acsami.2c00564 ↗
19. 10.1021/acs.jcim.1c0056610.1021/acs.jcim.1c00566 ↗
20. 10.1002/adts.20210056510.1002/adts.202100565 ↗
21. 10.1016/j.jechem.2021.01.03510.1016/j.jechem.2021.01.035 ↗
22. 10.1016/j.actamat.2021.11743110.1016/j.actamat.2021.117431 ↗
23. 10.1021/acsomega.2c0138010.1021/acsomega.2c01380 ↗
24. 10.1016/j.chemolab.2018.04.00410.1016/j.chemolab.2018.04.004 ↗
25. Lundberg, S. M.; Erion, G. G.; Lee, S.I. Consistent Individualized Feature Attribution for Tree Ensembles, arXiv:1802.03888, arXiv 2017.
26. Lundberg, S. M.; Lee, S.I. A Unified Approach to Interpreting Model Predictions, arXiv:1705.07874, arXiv 2017.
27. 10.3390/batteries901001310.3390/batteries9010013 ↗
28. 10.31449/inf.v44i4.302310.31449/inf.v44i4.3023 ↗
29. 10.20517/jmi.2022.0710.20517/jmi.2022.07 ↗
30. 10.1016/S0167-2738(01)00684-110.1016/S0167-2738(01)00684-1 ↗
31. 10.1149/06101.0151ecst10.1149/06101.0151ecst ↗
32. 10.1017/S026988890000202210.1017/S0269888900002022 ↗
33. 10.1103/PhysRevB.103.03540710.1103/PhysRevB.103.035407 ↗
34. 10.1088/1361-648X/aa98bd10.1088/1361-648X/aa98bd ↗
35. 10.1016/j.cocom.2022.e0066710.1016/j.cocom.2022.e00667 ↗
36. 10.1016/j.ssi.2004.06.00210.1016/j.ssi.2004.06.002 ↗
37. 10.1039/B905911N10.1039/B905911N ↗
38. 10.11949/0438-1157.2021136910.11949/0438-1157.20211369 ↗
39. 10.1016/S0167-2738(99)00337-910.1016/S0167-2738(99)00337-9 ↗
40. 10.1016/j.seppur.2020.11736110.1016/j.seppur.2020.117361 ↗
41. 10.1016/j.ssi.2007.12.09910.1016/j.ssi.2007.12.099 ↗
42. 10.1016/j.ssi.2004.07.03610.1016/j.ssi.2004.07.036 ↗
43. 10.1016/0167-2738(82)90045-510.1016/0167-2738(82)90045-5 ↗
44. 10.1002/adma.20110335210.1002/adma.201103352 ↗
45. 10.1016/S0167-2738(96)00463-810.1016/S0167-2738(96)00463-8 ↗
46. C B. J. · Chem. Mater. · 1998 · 10 · 287010.1021/cm980236q ↗
47. 10.1021/jp062886k10.1021/jp062886k ↗
48. 10.1103/PhysRevLett.100.23550410.1103/PhysRevLett.100.235504 ↗
49. Chunrong P. · Comput. Appl. Chem. · 2009 · 26 · 1451
50. 10.1016/j.commatsci.2009.04.04710.1016/j.commatsci.2009.04.047 ↗
51. 10.1016/j.chemphys.2022.11151110.1016/j.chemphys.2022.111511 ↗
52. 10.3390/cryst1207094710.3390/cryst12070947 ↗