Machine learning--based discovery of novel oxide and halide perovskites for energy storage
Source abstract
Abstract
In this study, the novel oxide and halide perovskite compounds in the form of single and double perovskite are explored by using machine learning, density functional theory databases, and experimental databases. The important features that define the formability and stability of oxide perovskite and halide perovskite compounds are extracted. Using these datasets as training datasets, very precise machine learning classification models are prepared using random forest classifiers for formability and stability. Subsequently, these results are cross-validated to screen the potential novel compounds. Further, the hierarchical clustering technique is used to understand the effect of multi-collinearity among selected features and also to analyze their effect on perovskite formability and stability. Our machine learning model predicts 591 novel perovskite compounds which are formable as well as stable. Further, the charge capacity of these novel compounds is also analyzed for battery applications.
Source: expertdata · Quality: candidate unverified · Source record ↗
Research context
OpenAlex topics: Perovskite Materials and Applications · Advanced Thermoelectric Materials and Devices · Transition Metal Oxide Nanomaterials
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (60)
Show source-provided references
1. Würfel · 2016 · 171
2. Complex thermoelectric materials10.1038/nmat2090 ↗
3. Effect of electron–phonon coupling on transport properties of monolayer germanene: A thermoelectric perspective10.1016/j.mssp.2022.107115 ↗
4. Battery materials design essentials10.1021/accountsmr.1c00026 ↗
5. On battery materials and methods
6. Optical properties of perovskite oxides in their paraelectric and ferroelectric phases10.1103/PhysRev.166.565 ↗
7. Glory of piezoelectric perovskites10.1088/1468-6996/16/4/046001 ↗
8. Perovskite oxides for visible-light-absorbing ferroelectric and photovoltaic materials10.1038/nature12622 ↗
9. Inorganic and hybrid organo-metal perovskite nanostructures: synthesis, properties, and applications10.1002/adfm.201603752 ↗
10. Metal halide perovskite nanostructures for optoelectronic applications and the study of physical properties10.1038/s41578-019-0080-9 ↗
11. Perovskite oxide-based photocatalysts for solar-driven hydrogen production: Progress and perspectives10.1016/j.solener.2020.09.078 ↗
12. Perovskite-based solar cells10.1126/science.1245473 ↗
13. Halide perovskites: thermal transport and prospects for thermoelectricity
14. Accelerated development of perovskite-inspired materials via high-throughput synthesis and machine-learning diagnosis10.1016/j.joule.2019.05.014 ↗
15. Halide perovskite materials for energy storage applications10.1002/adfm.202003653 ↗
16. Progress on perovskite materials for energy application10.1016/j.rechem.2022.100321 ↗
17. Stability of metal complexes
18. High-throughput dft calculations of formation energy, stability and oxygen vacancy formation energy of abo3 perovskites10.1038/sdata.2017.153 ↗
19. The phase diagram of a mixed halide (br, i) hybrid perovskite obtained by synchrotron x-ray diffraction10.1039/C8RA09398A ↗
20. Perovskites: A new generation electrode materials for storage applications10.1016/j.jpowsour.2023.233166 ↗
21. Halide perovskites for applications beyond photovoltaics10.1002/smtd.201700310 ↗
22. Fully textured monolithic perovskite/silicon tandem solar cells with 25.2% power conversion efficiency10.1038/s41563-018-0115-4 ↗
23. Mixed perovskite (mapbi3-xclx) solar cells using light-emitting conjugated polymer dmp end-capped mdmo-ppv as a hole transport material10.1016/j.jksus.2022.102262 ↗
24. A machine learning approach for the prediction of formability and thermodynamic stability of single and double perovskite oxides10.1021/acs.chemmater.0c03402 ↗
25. Ordered meso-and macroporous perovskite oxide catalysts for emerging applications10.1039/C8CC01239C ↗
26. Crystal structures
27. What defines a halide perovskite?10.1021/acsenergylett.0c00039 ↗
28. Mn and co co-doped perovskite fluorides knif3 with enhanced capacitive performance10.1016/j.jcis.2019.09.051 ↗
29. Conversion-type nicomn triple perovskite fluorides for advanced aqueous supercapacitors, batteries and supercapatteries10.1039/D1CC02488D ↗
30. Perovskite fluoride nanif3 with hollow micron sphere structure as anode for li-ion hybrid capacitors10.1007/s12598-022-02047-5 ↗
31. Application of a clustered countercurrent-flow micro-channel reactor in the preparation of kmnf 3 perovskite for asymmetric supercapacitors10.1039/D0RA01411G ↗
32. Revised values of effective ionic radii10.1107/S0567740870003576 ↗
33. Formability of abo3 perovskites10.1016/j.jallcom.2003.10.017 ↗
34. Structural stability and formability of abo3-type perovskite compounds10.1107/S0108768107046174 ↗
35. Thermodynamic stability trend of cubic perovskites10.1021/jacs.7b09379 ↗
36. M.R. Filip, F. Giustino, The geometric blueprint of perovskites, Proceedings of the National Academy of Sciences 115(21) (2018)5397-5402.10.1073/pnas.1719179115 ↗
37. Predicting the formation and stability of oxide perovskites by extracting underlying mechanisms using machine learning10.1016/j.commatsci.2022.111506 ↗
38. Predictions of new abo3 perovskite compounds by combining machine learning and density functional theory
39. A2b’b”o6 perovskites: a review10.1016/j.progsolidstchem.2014.08.001 ↗
40. Formability of abx3 (x= f, cl, br, i) halide perovskites10.1107/S0108768108032734 ↗
41. Thermodynamic stability landscape of halide double perovskites via high-throughput computing and machine learning10.1002/adfm.201807280 ↗
42. First principles high throughput screening of oxynitrides for water-splitting photocatalysts10.1039/C2EE23482C ↗
43. Machine learning bandgaps of double perovskites10.1038/srep19375 ↗
44. Data-based methods for materials design and discovery: Basic ideas and general methods
45. Scikit-learn: Machine learning in python
46. Experiments on the homo-lumo nature of metal-metal bonds10.1002/anie.197906901 ↗
47. A pseudopotential viewpoint of the electronic and structural properties of crystals
48. Vii. note on regression and inheritance in the case of two parents10.1098/rspl.1895.0041 ↗
49. Random forests10.1023/A:1010933404324 ↗
50. Foundations of data imbalance and solutions for a data democracy
51. Gaussian processes for machine learning10.1142/S0129065704001899 ↗
52. Williams · 2006
53. Bayesian approach for inferrable machine learning models of process–structure–property linkages in complex concentrated alloys10.1016/j.jallcom.2023.171595 ↗
54. A unified approach to interpreting model predictions
55. From local explanations to global understanding with explainable ai for trees10.1038/s42256-019-0138-9 ↗
56. Spearman’s rank correlation coefficient
57. Learning representations from dendrograms10.1007/s10994-020-05895-3 ↗
58. E.J.T.O.P. Peterson, et al., Scipy: Open source scientific tools for python.(2001), Reference Source (2001).
59. Perovskite crystals: Unique pseudo-jahn–teller origin of ferroelectricity, multiferroicity, permittivity, flexoelectricity, and polar nanoregions10.3390/condmat5040068 ↗
60. Batteries ∣ capacity