journal article·2025-08-21Open access

Machine Learning Models for Predicting Electronic Coupling in TEMPO/TEMPO + Systems

Souvik Mitra, Clara Zens, Stephan Kupfer, Andreas Heuer, Diddo Diddens

The Journal of Physical Chemistry C· Volume 129· Issue 33

Abstract

High Resolution Image Download MS PowerPoint Slide Organic radical batteries (ORBs) based on the TEMPO (2,2,6,6-tetramethylpiperidin-1-yl oxyl) radical have drawn significant attention, owing to their unique redox properties. A key factor influencing ORB’s redox properties, i.e., the kinetics of the electron transfer between the TEMPO–TEMPO + pairs, is the communication between the underlying redox-active states as given by the electronic coupling. However, due to the complex structure, predicting accurate electronic couplings for these pairs is computationally expensive and challenging. In this study, we introduce a machine learning (ML) workflow to predict the electronic coupling for TEMPO–TEMPO + pairs simply by their specific geometric orientations. For the ML models, a data set was generated through time-dependent density functional theory calculations coupled with the Generalized Mulliken Hush method to assess energies, (transition-)dipole moment, and couplings for specific TEMPO–TEMPO + configurations obtained from classical molecular dynamics simulations that mimic a realistic electrolyte environment. Our results demonstrate that, among the three ML models─linear regression, kernel ridge regression (KRR), and random forest─the KRR model, with its kernel-based approach, most effectively handles the correlated orientation-based descriptors. Moreover, our SHapley Additive exPlanations (SHAP)-based feature importance analysis indicates that multiple orientation factors jointly influence electronic coupling, rather than any single distance or angle dominating, with each parameter’s impact strongly contingent on the values of the others which is in agreement with previous studies computational by the consortium.
Source: openalex_inverted_index · Quality: baseline

Research context

OpenAlex topics: Machine Learning in Materials Science · Advanced Memory and Neural Computing · Catalysis and Oxidation Reactions

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

Affiliations

Institute of Physical Chemistry

Universität Münster

Friedrich Schiller University Jena

Helmholtz-Institute Münster (IMD-4)

Funding

Deutsche Forschungsgemeinschaft

References (49)

Show source-provided references
1. 10.1016/j.jpowsour.2019.02.02810.1016/j.jpowsour.2019.02.028 ↗
2. 10.1021/acsami.7b0040310.1021/acsami.7b00403 ↗
3. 10.1080/00268976.2013.78169510.1080/00268976.2013.781695 ↗
4. 10.1021/jp501628z10.1021/jp501628z ↗
5. 10.1063/1.169679210.1063/1.1696792 ↗
6. 10.1016/0304-4173(85)90014-X10.1016/0304-4173(85)90014-X ↗
7. 10.1002/anie.19931111310.1002/anie.199311113 ↗
8. 10.1016/0010-8545(85)80047-310.1016/0010-8545(85)80047-3 ↗
9. 10.1016/0304-4173(85)90014-X10.1016/0304-4173(85)90014-X ↗
10. 10.1021/acs.chemrev.5b0029810.1021/acs.chemrev.5b00298 ↗
11. 10.1063/5.022180210.1063/5.0221802 ↗
12. 10.1021/jp061184s10.1021/jp061184s ↗
13. 10.1021/acs.jpca.9b0425610.1021/acs.jpca.9b04256 ↗
14. 10.1039/c002337j10.1039/c002337j ↗
15. 10.1021/ja061827h10.1021/ja061827h ↗
16. 10.1038/s41598-023-37308-510.1038/s41598-023-37308-5 ↗
17. 10.1021/acs.jctc.3c0125210.1021/acs.jctc.3c01252 ↗
18. 10.1039/D3CP04111E10.1039/D3CP04111E ↗
19. 10.1002/jcc.2122410.1002/jcc.21224 ↗
20. Abraham, M.; Alekseenko, A.; Bergh, C.; Blau, C.; Briand, E.; Doijade, M.; Fleischmann, S.; Gapsys, V.; Garg, G.; Gorelov, S. GROMACS 2023 Manual. 2023 10.5281/zenodo.7588711.10.5281/zenodo.7588711 ↗
21. Rapaport D. · 200410.1017/CBO9780511816581 ↗
22. 10.1021/ja962176010.1021/ja9621760 ↗
23. 10.1063/1.45615310.1063/1.456153 ↗
24. Frisch, M. J.; Trucks, G. W.; Schlegel, H. B.; Scuseria, G. E.; Robb, M. A.; Cheeseman, J. R.; Scalmani, G.; Barone, V.; Petersson, G. A.; Nakatsuji, H. Gaussian1̃6 Revision C.01 ; Gaussian Inc.: Wallingford CT, 2016.
25. 10.1039/b810189b10.1039/b810189b ↗
26. 10.1007/s00214-010-0846-z10.1007/s00214-010-0846-z ↗
27. 10.1039/C4CP04286G10.1039/C4CP04286G ↗
28. 10.1002/wcms.160610.1002/wcms.1606 ↗
29. 10.1002/wcms.8110.1002/wcms.81 ↗
30. 10.1002/jcc.2288510.1002/jcc.22885 ↗
31. 10.1021/acs.jctc.2c0071810.1021/acs.jctc.2c00718 ↗
32. 10.1103/PhysRevLett.108.05830110.1103/PhysRevLett.108.058301 ↗
33. 10.1021/acs.jpca.0c0436810.1021/acs.jpca.0c04368 ↗
34. 10.1002/aic.1676010.1002/aic.16760 ↗
35. 10.1002/adts.20180013610.1002/adts.201800136 ↗
36. Hastie T. · 200910.1007/978-0-387-84858-7 ↗
37. Schölkopf B. · 2002
38. 10.1023/A:101093340432410.1023/A:1010933404324 ↗
39. 10.1007/s11222-016-9646-110.1007/s11222-016-9646-1 ↗
40. Pedregosa F. · J. Mach. Learn. Res. · 2011 · 12 · 2825
41. Bishop C. M. · 2006
42. 10.1007/s10115-013-0679-x10.1007/s10115-013-0679-x ↗
43. Lundberg, S.; Lee, S.I. A Unified Approach to Interpreting Model Predictions, 2017. arXiv:1705.07874. arXiv.org e-Print archive. https://arxiv.org/abs/1705.07874.
44. 10.12688/f1000research.17555.110.12688/f1000research.17555.1 ↗
45. Lundberg, S. M.; Lee, S.I. SHAP: SHapley Additive exPlanations 2017 https://shap.readthedocs.io/en/latest/.
46. 10.1021/acs.jctc.0c0118910.1021/acs.jctc.0c01189 ↗
47. 10.1063/5.004861810.1063/5.0048618 ↗
48. 10.1021/acs.jctc.1c0092110.1021/acs.jctc.1c00921 ↗
49. 10.1038/s41598-024-60063-010.1038/s41598-024-60063-0 ↗