journal article·2023-07

Explainable machine learning for predicting the band gaps of ABX3 perovskites

David O. Obada, Emmanuel Okafor, Simeon A. Abolade, Aniekan M. Ukpong, David Dodoo-Arhin, Akinlolu Akande

Publisher page

Abstract

In this study, we trained and compared explainable machine learning algorithms for predicting the band gaps of perovskite materials that have the formula ABX 3 containing both zero and non-zero band gaps. Six supervised learning models: 5 ensemble learning methods and 1 neural network (CompoundNet) were employed to study the non-linear relationship that exists between the band gap and the characteristics of its constituent elements such as electronegativity, covalent radius, first ionization energy, and row in the periodic table. The machine learning (ML) models were trained on datasets obtained from density functional theory (DFT) calculations. The results show that CatBoost and XGBoost models yielded the least predictive errors and the highest coefficient of determination of R 2 ≥ 88% than other approaches in the testing phase. Furthermore, the Shapley Additive Explanation (SHAP) was used for explaining the model based on the elemental composition of each perovskite compound from the physics standpoint, and a novel holistic feature ranking of the explained models was proposed. One key insight gained from the SHAP analysis is that the Pauling electronegativity of the B site cation in the cubic perovskites which characteristically plays an important role in the electronic properties of this class of materials is the feature that contributes most to the prediction of the band gaps. These results reveal the potential of ML to predict materials properties quickly and accurately with datasets useful in the engineering of efficient solar cell devices.
Source: expertdata · Quality: candidate unverified · Source record ↗

Research context

OpenAlex topics: Machine Learning in Materials Science · Perovskite Materials and Applications · Electronic and Structural Properties of Oxides

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

References (44)

Show source-provided references
1. Organometal halide perovskites as visible-light sensitizers for photovoltaic cells10.1021/ja809598r ↗
2. Epitaxial bifeo3 multiferroic thin film heterostructures10.1126/science.1080615 ↗
3. Temperature dependence of hole conductor free formamidinium lead iodide perovskite based solar cells10.1039/C4TA05149A ↗
4. Addressing the stability issue of perovskite solar cells for commercial applications10.1038/s41467-018-07255-1 ↗
5. Efficient, stable and scalable perovskite solar cells using poly (3-hexylthiophene)10.1038/s41586-019-1036-3 ↗
6. Inactive (pbi2) 2rbcl stabilizes perovskite films for efficient solar cells10.1126/science.abp8873 ↗
7. Study on bandgap predications of abx3-type perovskites by machine learning10.1016/j.orgel.2021.106426 ↗
8. High-performance large-area perovskite photovoltaic modules
9. Stable and high-efficiency methylammonium-free perovskite solar cells10.1002/adma.201905502 ↗
10. Universal energy level tailoring of self-organized hole extraction layers in organic solar cells and organic–inorganic hybrid perovskite solar cells10.1039/C5EE03560K ↗
11. Localization and delocalization errors in density functional theory and implications for band-gap prediction10.1103/PhysRevLett.100.146401 ↗
12. Energy band gaps and lattice parameters evaluated with the heyd-scuseria-ernzerhof screened hybrid functional10.1063/1.2085170 ↗
13. Self-consistent g w calculations for semiconductors and insulators10.1103/PhysRevB.75.235102 ↗
14. Data-driven design of high-performance masnxpb1-xi3 perovskite materials by machine learning and experimental realization10.1038/s41377-022-00924-3 ↗
15. Predicting the formation and stability of oxide perovskites by extracting underlying mechanisms using machine learning10.1016/j.commatsci.2022.111506 ↗
16. Data-driven analysis of hole-transporting materials for perovskite solar cells performance10.1021/acs.jpcc.2c04725 ↗
17. The utility of composition-based machine learning models for band gap prediction10.1016/j.commatsci.2021.110637 ↗
18. Density functional theory–machine learning approach to analyze the bandgap of elemental halide perovskites and ruddlesden-popper phases10.1002/cphc.201800382 ↗
19. Prediction model of band gap for inorganic compounds by combination of density functional theory calculations and machine learning techniques10.1103/PhysRevB.93.115104 ↗
20. Machine learning for predicting the band gaps of abx3 perovskites from elemental properties10.1021/acs.jpcc.9b11768 ↗
21. Band gap and band alignment prediction of nitride-based semiconductors using machine learning10.1039/C8TC05554H ↗
22. Machine learning bandgaps of double perovskites10.1038/srep19375 ↗
23. Discovery of direct band gap perovskites for light harvesting by using machine learning10.1016/j.commatsci.2022.111476 ↗
24. Predictive design model for low-dimensional organic–inorganic halide perovskites assisted by machine learning10.1021/jacs.1c05441 ↗
25. Explainable machine-learning predictions for the prevention of hypoxaemia during surgery10.1038/s41551-018-0304-0 ↗
26. Stability and electronic properties of new inorganic perovskites from high-throughput ab initio calculations10.1039/C5TC04172D ↗
27. Revised effective ionic radii and systematic studies of interatomic distances in halides and chalcogenides10.1107/S0567739476001551 ↗
28. Efficient iterative schemes for ab initio total-energy calculations using a plane-wave basis set10.1103/PhysRevB.54.11169 ↗
29. Generalized gradient approximation made simple10.1103/PhysRevLett.77.3865 ↗
30. A general-purpose machine learning framework for predicting properties of inorganic materials10.1038/npjcompumats.2016.28 ↗
31. Machine learning energies of 2 million elpasolite (a b c 2 d 6) crystals10.1103/PhysRevLett.117.135502 ↗
32. Machine learning the band gap properties of kesterite i 2- ii- iv- v 4 quaternary compounds for photovoltaics applications
33. D. P. Kingma, J. Ba, Adam: A method for Stochastic Optimization, arXiv preprint arXiv:1412.6980.
34. Random forests10.1023/A:1010933404324 ↗
35. Analysis of a random forests model
36. Top 10 algorithms in data mining10.1007/s10115-007-0114-2 ↗
37. Maimon · 2014 · vol. 81
38. Xgboost: a scalable tree boosting system
39. L. Prokhorenkova, G. Gusev, A. Vorobev, A. V. Dorogush, A. Gulin, Catboost: unbiased boosting with categorical features, Adv. Neural Inf. Process. Syst. 31.
40. G. Ke, Q. Meng, T. Finley, T. Wang, W. Chen, W. Ma, Q. Ye, T.-Y. Liu, Lightgbm: a highly efficient gradient boosting decision tree, Adv. Neural Inf. Process. Syst. 30.
41. S. M. Lundberg, S.-I. Lee, A unified approach to interpreting model predictions, Adv. Neural Inf. Process. Syst. 30.
42. Trends in energy gaps of binary compounds: an approach based upon electron transfer parameters from optical spectroscopy10.1088/0022-3719/13/16/008 ↗
43. Modeling energy band gap as a function of optical electronegativity for binary oxides
44. Proposed phase relations in the hfo 2-rich portion of the system hf–hfo 210.1111/j.1151-2916.1973.tb12432.x ↗