Temporal Decoupling-Based Machine Learning Framework for Precise Efficiency Prediction in Perovskite Solar Cells
Source abstract
Abstract
The rapid and accurate identification of potential high-efficiency design strategies for perovskite solar cells (PSCs) is of paramount importance in advancing their development and commercialization. However, the application of machine learning (ML) algorithms in this field is hindered by unstable PSC data sets (e.g., time-related noise and data imbalance). Here, we introduce a ML framework specifically tailored for temporal decoupling through feature engineering and uncertainty modeling (noise processing techniques) to accurately predict the efficiency of PSCs. In our framework, we utilize one-hot encoding and feature fusion methods to extract features from a shared data set encompassing perovskite material, processing, and PSC architecture. After temporal decoupling, our ML model shows an outstanding precision of 96.88% and a specificity of 99.3% for high-efficiency devices and is successfully applied to predict PSC efficiencies in the period between 2021 and 2023. This temporal decoupling ML framework also reveals hidden relationships between features and efficiency through cross-feature analysis. Our work demonstrates the potential of ML for predicting performance and elucidates the associated mechanisms, accelerating PSC commercialization and reducing costs.
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: Perovskite Materials and Applications · Machine Learning in Materials Science · Machine Learning and ELM
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
School of Microelectronics, University of Science and Technology of China, Hefei 230026, China
3rd Institute of Physics, University of Stuttgart, Stuttgart 70569, Germany
National Synchrotron Radiation Laboratory, University of Science and Technology of China, Hefei 230029, China
Funding
University of Science and Technology of China · National Natural Science Foundation of China
References (63)
Show source-provided references
1. 10.1038/s41563-023-01705-y10.1038/s41563-023-01705-y ↗
2. 10.1021/acsenergylett.2c0281810.1021/acsenergylett.2c02818 ↗
3. 10.1007/s40684-022-00417-z10.1007/s40684-022-00417-z ↗
4. 10.1002/aenm.20220385910.1002/aenm.202203859 ↗
5. 10.1103/PhysRevLett.120.14530110.1103/PhysRevLett.120.145301 ↗
6. 10.1038/s41524-023-01068-710.1038/s41524-023-01068-7 ↗
7. Ye, W.; Chen, C.; Wang, Z.; Chu, I.H.; Ong, S. P. Deep neural networks for accurate predictions of garnet stability, 2017. arXiv:1712.01908. arXiv preprint. https://doi.org/10.48550/arXiv.1712.01908.10.1038/s41467-018-06322-x ↗
8. 10.1002/aenm.20190189110.1002/aenm.201901891 ↗
9. 10.1038/s41377-022-00924-310.1038/s41377-022-00924-3 ↗
10. 10.1016/j.jechem.2022.10.02410.1016/j.jechem.2022.10.024 ↗
11. 10.1038/s41560-021-00941-310.1038/s41560-021-00941-3 ↗
12. 10.1002/aenm.20220146310.1002/aenm.202201463 ↗
13. 10.1002/solr.20210092710.1002/solr.202100927 ↗
14. 10.1016/j.jechem.2023.07.01810.1016/j.jechem.2023.07.018 ↗
15. 10.1021/acsenergylett.0c0089910.1021/acsenergylett.0c00899 ↗
16. 10.1016/j.nanoen.2018.11.06910.1016/j.nanoen.2018.11.069 ↗
17. National Renewable Energy Laboratory (NREL). 2024, https://www.nrel.gov/pv/cell-efficiency.html (accessed March 2 2024).
18. 10.1002/cssc.20170109510.1002/cssc.201701095 ↗
19. Abu-Mostafa Y. S. · 2012
20. Gers F. · 2001
21. 10.1021/acsenergylett.2c0255510.1021/acsenergylett.2c02555 ↗
22. Zheng A. · 2018
23. Juan, Y.; Zhuang, Y.; Chin, W.S.; Lin, C.J. Field-aware factorization machines for CTR prediction. Proceedings of the 10th ACM Conference on Recommender Systems, 2016; pp 43–50.10.1145/2959100.2959134 ↗
24. 10.1038/s41524-020-0307-810.1038/s41524-020-0307-8 ↗
25. 10.1039/D1TA08194B10.1039/D1TA08194B ↗
26. The Perovskite Database. 2023, https://www.perovskitedatabase.com (accessed Sept 5, 2023).
27. 10.1002/inf2.1232210.1002/inf2.12322 ↗
28. 10.1002/inf2.1239310.1002/inf2.12393 ↗
29. Van der Maaten L. · J. Mach. Learn. Res. · 2008 · 9 · 2579
30. 10.1109/ACCESS.2023.329854210.1109/ACCESS.2023.3298542 ↗
31. 10.1002/inf2.1242510.1002/inf2.12425 ↗
32. 10.1038/s41524-019-0177-010.1038/s41524-019-0177-0 ↗
33. 10.1016/j.commatsci.2020.11019110.1016/j.commatsci.2020.110191 ↗
34. Bishop, C. Pattern Recognition and Machine Learning; Springer, 2006; Vol. 2, pp 35–42.
35. 10.1016/j.inffus.2021.11.00510.1016/j.inffus.2021.11.005 ↗
36. 10.1002/solr.20210110010.1002/solr.202101100 ↗
37. 10.1002/ente.20210094810.1002/ente.202100948 ↗
38. 10.1016/j.nanoen.2022.10739410.1016/j.nanoen.2022.107394 ↗
39. 10.1109/4235.58589310.1109/4235.585893 ↗
40. 10.1038/s41467-018-05761-w10.1038/s41467-018-05761-w ↗
41. 10.1016/j.jmat.2022.04.00610.1016/j.jmat.2022.04.006 ↗
42. 10.1038/s41467-020-17945-410.1038/s41467-020-17945-4 ↗
43. 10.1016/j.commatsci.2022.11147610.1016/j.commatsci.2022.111476 ↗
44. He, K.; Zhang, X.; Ren, S.; Sun, J. Deep residual learning for image recognition. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016; pp 770–778.10.1109/CVPR.2016.90 ↗
45. Vaswani A. · 2017 · 30
46. Liu, Z.; Lin, Y.; Cao, Y.; Hu, H.; Wei, Y.; Zhang, Z.; Lin, S.; Guo, B. Swin transformer: Hierarchical vision transformer using shifted windows. In Proceedings of the IEEE/CVF international conference on computer vision, 2021; pp 10012–10022.10.1109/ICCV48922.2021.00986 ↗
47. Ke G. · 2017 · 30 · 3149
48. Prokhorenkova L. · 2018 · 31 · 6639
49. Snoek J. · 2012 · 25 · 2951
50. 10.1039/d3ee01801f10.1039/d3ee01801f ↗
51. 10.1002/aenm.20230259410.1002/aenm.202302594 ↗
52. 10.1016/j.solmat.2022.11205510.1016/j.solmat.2022.112055 ↗
53. 10.1613/jair.95310.1613/jair.953 ↗
54. Chen, T.; Guestrin, C. Xgboost: A scalable tree boosting system. In Proceedings of the 22nd acm sigkdd International Conference on Knowledge Discovery and Data Mining, 2016; pp 785–794.10.1145/2939672.2939785 ↗
55. 10.1111/j.2517-6161.1996.tb02080.x10.1111/j.2517-6161.1996.tb02080.x ↗
56. 10.1080/00401706.1970.1048863410.1080/00401706.1970.10488634 ↗
57. 10.1021/acsami.2c0616310.1021/acsami.2c06163 ↗
58. 10.1039/D0TA11564A10.1039/D0TA11564A ↗
59. 10.1039/D1EE02095A10.1039/D1EE02095A ↗
60. 10.1049/mnl.2019.073510.1049/mnl.2019.0735 ↗
61. 10.1016/j.joule.2021.11.01310.1016/j.joule.2021.11.013 ↗
62. 10.1039/C5CP05371D10.1039/C5CP05371D ↗
63. 10.1021/acs.jpcc.2c0472510.1021/acs.jpcc.2c04725 ↗